if you need more than one keyword, modify and separate by underscore _
the list of search keywords can be up to 50 characters long
if you modify the keywords, press enter within the field to confirm the new search key
Tag: adversarial
Bibliography items where occurs: 162
- The AI Index 2022 Annual Report / 2205.03468 / ISBN:https://doi.org/10.48550/arXiv.2205.03468 / Published by ArXiv / on (web) Publishing site
- Chapter 3 Technical AI Ethics
Chapter 5 AI Policy and Governance
Appendix - AI Ethics Issues in Real World: Evidence from AI Incident Database / 2206.07635 / ISBN:https://doi.org/10.48550/arXiv.2206.07635 / Published by ArXiv / on (web) Publishing site
- 2 Related Work
References - The Different Faces of AI Ethics Across the World: A Principle-Implementation Gap Analysis / 2206.03225 / ISBN:https://doi.org/10.48550/arXiv.2206.03225 / Published by ArXiv / on (web) Publishing site
- 5 Evaluation of Ethical Principle Implementations
References - Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society / 2001.04335 / ISBN:https://doi.org/10.48550/arXiv.2001.04335 / Published by ArXiv / on (web) Publishing site
- 2 The Near-Long
Recommendations and Conclusion - On the Current and Emerging Challenges of Developing Fair and Ethical AI Solutions in Financial Services / 2111.01306 / ISBN:https://doi.org/10.48550/arXiv.2111.01306 / Published by ArXiv / on (web) Publishing site
- 3 Practical Challengesof Ethical AI
References - Implementing Responsible AI: Tensions and Trade-Offs Between Ethics Aspects / 2304.08275 / ISBN:https://doi.org/10.48550/arXiv.2304.08275 / Published by ArXiv / on (web) Publishing site
- II. Underlying Aspects
III. Interactions between Aspects
References - Ethical Considerations and Policy Implications for Large Language Models: Guiding Responsible Development and Deployment / 2308.02678 / ISBN:https://doi.org/10.48550/arXiv.2308.02678 / Published by ArXiv / on (web) Publishing site
- References
- Dual Governance: The intersection of centralized regulation and crowdsourced safety mechanisms for Generative AI / 2308.04448 / ISBN:https://doi.org/10.48550/arXiv.2308.04448 / Published by ArXiv / on (web) Publishing site
- 2 Background
5 Crowdsourced safety mechanism - A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation / 2305.11391 / ISBN:https://doi.org/10.48550/arXiv.2305.11391 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
3 Vulnerabilities, Attack, and Limitations
5 Falsification and Evaluation
6 Verification
7 Runtime Monitor
Reference - Targeted Data Augmentation for bias mitigation / 2308.11386 / ISBN:https://doi.org/10.48550/arXiv.2308.11386 / Published by ArXiv / on (web) Publishing site
- 2 Related works
References - The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward / 2308.14253 / ISBN:https://doi.org/10.48550/arXiv.2308.14253 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
2 The evolution of artificial intelligence: from theory to general capabilities
3 Emerging dual-use risks and vulnerabilities in AI systems
5 Research directions in AI safety and violet teaming
7 Violet teaming to address dual-use risks of AI in biotechnology
10 Supplemental & additional details
References - The AI Revolution: Opportunities and Challenges for the Finance Sector / 2308.16538 / ISBN:https://doi.org/10.48550/arXiv.2308.16538 / Published by ArXiv / on (web) Publishing site
- Table of contents and index
2 Key AI technology in financial services - Ethical Framework for Harnessing the Power of AI in Healthcare and Beyond / 2309.00064 / ISBN:https://doi.org/10.48550/arXiv.2309.00064 / Published by ArXiv / on (web) Publishing site
- 6 Way forward
- Pathway to Future Symbiotic Creativity / 2209.02388 / ISBN:https://doi.org/10.48550/arXiv.2209.02388 / Published by ArXiv / on (web) Publishing site
- Introduction
Part 1 - 1 Generatives Systems: Mimicking Artifacts
Part 1 - 2 Appreciate Systems: Mimicking Styles
Part 1 - 3 Artistic Systems: Mimicking Inspiration
Part 3 - 2 Machine Artist Models
References - FUTURE-AI: Guiding Principles and Consensus Recommendations for Trustworthy Artificial Intelligence in Medical Imaging / 2109.09658 / ISBN:https://doi.org/10.48550/arXiv.2109.09658 / Published by ArXiv / on (web) Publishing site
- 2. Fairness - For Equitable AI in Medical Imaging
6. Robustness - For Reliable AI in Medical Imaging
7. Explainability - For Enhanced Understanding of AI in Medical Imaging
9. Discussion and Conclusion
References - Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities / 2310.08565 / ISBN:https://doi.org/10.48550/arXiv.2310.08565 / Published by ArXiv / on (web) Publishing site
- I. Introduction and Motivation
III. Survey Approach & Taxonomy
IV. Attack Surfaces
VI. Human-Robot Interaction (HRI) Security Studies
VII. Future Research & Discussion
References - Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Risks / 2310.07879 / ISBN:https://doi.org/10.48550/arXiv.2310.07879 / Published by ArXiv / on (web) Publishing site
- 4 Taxonomy of AI Privacy Risks
References - ClausewitzGPT Framework: A New Frontier in Theoretical Large Language Model Enhanced Information Operations / 2310.07099 / ISBN:https://doi.org/10.48550/arXiv.2310.07099 / Published by ArXiv / on (web) Publishing site
- Theoretical Impact of LLMs on
Information Operations
- A Review of the Ethics of Artificial Intelligence and its Applications in the United States / 2310.05751 / ISBN:https://doi.org/10.48550/arXiv.2310.05751 / Published by ArXiv / on (web) Publishing site
- 3. AI Ethical Principles
- A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics / 2310.05694 / ISBN:https://doi.org/10.48550/arXiv.2310.05694 / Published by ArXiv / on (web) Publishing site
- REFERENCES
- The Return on Investment in AI Ethics: A Holistic Framework / 2309.13057 / ISBN:https://doi.org/10.48550/arXiv.2309.13057 / Published by ArXiv / on (web) Publishing site
- 4. A Holistic Framework
- An Evaluation of GPT-4 on the ETHICS Dataset / 2309.10492 / ISBN:https://doi.org/10.48550/arXiv.2309.10492 / Published by ArXiv / on (web) Publishing site
- 4 Discussion
- Responsible AI Pattern Catalogue: A Collection of Best Practices for AI Governance and Engineering / 2209.04963 / ISBN:https://doi.org/10.48550/arXiv.2209.04963 / Published by ArXiv / on (web) Publishing site
- 5 Product Patterns
- FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare / 2309.12325 / ISBN:https://doi.org/10.48550/arXiv.2309.12325 / Published by ArXiv / on (web) Publishing site
- METHODS
FUTURE-AI GUIDELINE - Specific versus General Principles for Constitutional AI / 2310.13798 / ISBN:https://doi.org/10.48550/arXiv.2310.13798 / Published by ArXiv / on (web) Publishing site
- 4 Reinforcement Learning with Good-for-Humanity Preference Models
References - Unpacking the Ethical Value Alignment in Big Models / 2310.17551 / ISBN:https://doi.org/10.48550/arXiv.2310.17551 / Published by ArXiv / on (web) Publishing site
- 3 Investigating the Ethical Values of
Large Language Models
References - Towards Effective Paraphrasing for Information
Disguise / 2311.05018 / ISBN:https://doi.org/10.1007/978-3-031-28238-6_22 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
2 Related Work
References - Unlocking the Potential of ChatGPT: A Comprehensive Exploration of its Applications, Advantages, Limitations, and Future Directions in Natural Language Processing / 2304.02017 / ISBN:https://doi.org/10.48550/arXiv.2304.02017 / Published by ArXiv / on (web) Publishing site
- 6 Limitations and potential challenges
7 Ethical considerations when using ChatGPT
References - Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies / 2304.07683 / ISBN:https://doi.org/10.48550/arXiv.2304.07683 / Published by ArXiv / on (web) Publishing site
- IV. Mitigation strategies for bias in AI
- A Brief History of Prompt: Leveraging Language Models. (Through Advanced Prompting) / 2310.04438 / ISBN:https://doi.org/10.48550/arXiv.2310.04438 / Published by ArXiv / on (web) Publishing site
- References
- She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models / 2310.18333 / ISBN:https://doi.org/10.48550/arXiv.2310.18333 / Published by ArXiv / on (web) Publishing site
- 2 Related Works
References - How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities / 2311.09447 / ISBN:https://doi.org/10.48550/arXiv.2311.09447 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
2 Related Work
3 Methodology
4 Experiments
5 Conclusion
References - Prudent Silence or Foolish Babble? Examining Large Language Models' Responses to the Unknown / 2311.09731 / ISBN:https://doi.org/10.48550/arXiv.2311.09731 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
2 UnknownBench: Evaluating LLMs on the Unknown
4 Related Work
D Additional Results and Figures - Practical Cybersecurity Ethics: Mapping CyBOK to Ethical Concerns / 2311.10165 / ISBN:https://doi.org/10.48550/arXiv.2311.10165 / Published by ArXiv / on (web) Publishing site
- 3 Methodology
4 Findings
References - First, Do No Harm:
Algorithms, AI, and Digital Product Liability
Managing Algorithmic Harms Though Liability Law and Market Incentives / 2311.10861 / ISBN:https://doi.org/10.48550/arXiv.2311.10861 / Published by ArXiv / on (web) Publishing site
- Preface
- Case Repositories: Towards Case-Based Reasoning for AI Alignment / 2311.10934 / ISBN:https://doi.org/10.48550/arXiv.2311.10934 / Published by ArXiv / on (web) Publishing site
- 3 Related Work and Discussion
References - Responsible AI Considerations in Text Summarization Research: A Review of Current Practices / 2311.11103 / ISBN:https://doi.org/10.48550/arXiv.2311.11103 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
- RAISE -- Radiology AI Safety, an End-to-end lifecycle approach / 2311.14570 / ISBN:https://doi.org/10.48550/arXiv.2311.14570 / Published by ArXiv / on (web) Publishing site
- 4. Post-market surveillance phase
- Ethics and Responsible AI Deployment / 2311.14705 / ISBN:https://doi.org/10.48550/arXiv.2311.14705 / Published by ArXiv / on (web) Publishing site
- 4. Addressing bias, transparency, and accountability
11. References - Generative AI and US Intellectual Property Law / 2311.16023 / ISBN:https://doi.org/10.48550/arXiv.2311.16023 / Published by ArXiv / on (web) Publishing site
- II. US Patent law
References - Survey on AI Ethics: A Socio-technical Perspective / 2311.17228 / ISBN:https://doi.org/10.48550/arXiv.2311.17228 / Published by ArXiv / on (web) Publishing site
- 2 Privacy and data protection
4 Fairness and equity
5 Responsiblity, accountability, and regulations
References - Deepfakes, Misinformation, and Disinformation in the Era of Frontier AI, Generative AI, and Large AI Models / 2311.17394 / ISBN:https://doi.org/10.48550/arXiv.2311.17394 / Published by ArXiv / on (web) Publishing site
- II. Background
References - Understanding Teacher Perspectives and Experiences after Deployment of AI Literacy Curriculum in Middle-school Classrooms / 2312.04839 / ISBN:https://doi.org/10.48550/arXiv.2312.04839 / Published by ArXiv / on (web) Publishing site
- References
- Contra generative AI detection in higher education assessments / 2312.05241 / ISBN:https://doi.org/10.48550/arXiv.2312.05241 / Published by ArXiv / on (web) Publishing site
- References
- Intelligence Primer / 2008.07324 / ISBN:https://doi.org/10.48550/arXiv.2008.07324 / Published by ArXiv / on (web) Publishing site
- 7 Mathematically modeling intelligence
- Control Risk for Potential Misuse of Artificial Intelligence in Science / 2312.06632 / ISBN:https://doi.org/10.48550/arXiv.2312.06632 / Published by ArXiv / on (web) Publishing site
- References
- Disentangling Perceptions of Offensiveness: Cultural and Moral Correlates / 2312.06861 / ISBN:https://doi.org/10.48550/arXiv.2312.06861 / Published by ArXiv / on (web) Publishing site
- References
- Learning Human-like Representations to Enable Learning Human Values / 2312.14106 / ISBN:https://doi.org/10.48550/arXiv.2312.14106 / Published by ArXiv / on (web) Publishing site
- 2 Related Work
- Autonomous Threat Hunting: A Future Paradigm for AI-Driven Threat Intelligence / 2401.00286 / ISBN:https://doi.org/10.48550/arXiv.2401.00286 / Published by ArXiv / on (web) Publishing site
- 1. Introduction
2. Foundations of AI-driven threat intelligence
3. Autonomous threat hunting: conceptual framework
References - Exploring the Frontiers of LLMs in Psychological Applications: A Comprehensive Review / 2401.01519 / ISBN:https://doi.org/10.48550/arXiv.2401.01519 / Published by ArXiv / on (web) Publishing site
- 7. Challenges and future directions
- Synthetic Data in AI: Challenges, Applications, and Ethical Implications / 2401.01629 / ISBN:https://doi.org/10.48550/arXiv.2401.01629 / Published by ArXiv / on (web) Publishing site
- 2. The generation of synthetic data
3. The usage of synthetic data
4. Risks and Challenges in Utilizing Synthetic Datasets for AI
5. Conclusions
References - AI Ethics Principles in Practice: Perspectives of Designers and Developers / 2112.07467 / ISBN:https://doi.org/10.48550/arXiv.2112.07467 / Published by ArXiv / on (web) Publishing site
- V. Discussion and suggestions
References - Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models / 2310.19917 / ISBN:https://doi.org/10.48550/arXiv.2310.19917 / Published by ArXiv / on (web) Publishing site
- Discussion
- Towards Responsible AI in Banking: Addressing Bias for Fair Decision-Making / 2401.08691 / ISBN:https://doi.org/10.48550/arXiv.2401.08691 / Published by ArXiv / on (web) Publishing site
- Contents / List of figures / List of tables / Acronyms
3 Bias on demand: a framework for generating synthetic data with bias
II Mitigating bias - 5 Fairness mitigation
9 Towards fairness through time
Bibliography - Beyond principlism: Practical strategies for ethical AI use in research practices / 2401.15284 / ISBN:https://doi.org/10.48550/arXiv.2401.15284 / Published by ArXiv / on (web) Publishing site
- 1 The “Triple-Too” problem of AI ethics
3 Five specific goals and action-guiding strategies for ethical AI use in research practices - Detecting Multimedia Generated by Large AI Models: A Survey / 2402.00045 / ISBN:https://doi.org/10.48550/arXiv.2402.00045 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
3 Detection
5 Discussion
References - Trust and ethical considerations in a multi-modal, explainable AI-driven chatbot tutoring system: The case of collaboratively solving Rubik's Cubeà / 2402.01760 / ISBN:https://doi.org/10.48550/arXiv.2402.01760 / Published by ArXiv / on (web) Publishing site
- 2. Literature review
4. Discussion - Commercial AI, Conflict, and Moral Responsibility: A theoretical analysis and practical approach to the moral responsibilities associated with dual-use AI technology / 2402.01762 / ISBN:https://doi.org/10.48550/arXiv.2402.01762 / Published by ArXiv / on (web) Publishing site
- 4 Recommendations to address threats posed by crossover AI technology
References - POLARIS: A framework to guide the development of Trustworthy AI systems / 2402.05340 / ISBN:https://doi.org/10.48550/arXiv.2402.05340 / Published by ArXiv / on (web) Publishing site
- 2 Background
3 State of the practice
5 POLARIS framework application
References - Generative Artificial Intelligence in Healthcare: Ethical Considerations and Assessment Checklist / 2311.02107 / ISBN:https://doi.org/10.48550/arXiv.2311.02107 / Published by ArXiv / on (web) Publishing site
- Introduction
Reference - I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench / 2401.17882 / ISBN:https://doi.org/10.48550/arXiv.2401.17882 / Published by ArXiv / on (web) Publishing site
- 4 Awareness Dataset: AWAREEVAL
5 Experiments
A AWAREEVAL Dataset Details
B Experimental Settings & Results - Mapping the Ethics of Generative AI: A Comprehensive Scoping Review / 2402.08323 / ISBN:https://doi.org/10.48550/arXiv.2402.08323 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
3 Results
References - User Modeling and User Profiling: A Comprehensive Survey / 2402.09660 / ISBN:https://doi.org/10.48550/arXiv.2402.09660 / Published by ArXiv / on (web) Publishing site
- 4 Current Taxonomy
References - Evolving AI Collectives to Enhance Human Diversity and Enable Self-Regulation / 2402.12590 / ISBN:https://doi.org/10.48550/arXiv.2402.12590 / Published by ArXiv / on (web) Publishing site
- References
- What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents / 2402.13184 / ISBN:https://doi.org/10.48550/arXiv.2402.13184 / Published by ArXiv / on (web) Publishing site
- 2 Related Work
- The METRIC-framework for assessing data quality for trustworthy AI in medicine: a systematic review / 2402.13635 / ISBN:https://doi.org/10.48550/arXiv.2402.13635 / Published by ArXiv / on (web) Publishing site
- METRIC-framework for medical training data
- The European Commitment to Human-Centered Technology: The Integral Role of HCI in the EU AI Act's Success / 2402.14728 / ISBN:https://doi.org/10.48550/arXiv.2402.14728 / Published by ArXiv / on (web) Publishing site
- 2 The EU AI Act
- Autonomous Vehicles: Evolution of Artificial Intelligence and Learning Algorithms / 2402.17690 / ISBN:https://doi.org/10.48550/arXiv.2402.17690 / Published by ArXiv / on (web) Publishing site
- III. Ethical Considerations and Bias in AI-Driven
Software Development for Autonomous Vehicles
VI. AI and Learning Algorithms Statistics for Autonomous Vehicles
References - Envisioning the Applications and Implications of Generative AI for News Media / 2402.18835 / ISBN:https://doi.org/10.48550/arXiv.2402.18835 / Published by ArXiv / on (web) Publishing site
- References
- The Minimum Information about CLinical Artificial Intelligence Checklist for Generative Modeling Research (MI-CLAIM-GEN) / 2403.02558 / ISBN:https://doi.org/10.48550/arXiv.2403.02558 / Published by ArXiv / on (web) Publishing site
- Part 5. Interpretability of generative models
- Towards an AI-Enhanced Cyber Threat Intelligence Processing Pipeline / 2403.03265 / ISBN:https://doi.org/10.48550/arXiv.2403.03265 / Published by ArXiv / on (web) Publishing site
- II. Background & Literature Review
III. The AI-Enhanced CTI Processing Pipeline
IV. Challenges and Considerations
References - A Survey on Human-AI Teaming with Large Pre-Trained Models / 2403.04931 / ISBN:https://doi.org/10.48550/arXiv.2403.04931 / Published by ArXiv / on (web) Publishing site
- 3 Effective Human-AI Joint Systems
References - How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities / 2311.09447 / ISBN:https://doi.org/10.48550/arXiv.2311.09447 / Published by ArXiv / on (web) Publishing site
- B Baseline Setup
C Prompt Templates
D More Results - Responsible Artificial Intelligence: A Structured Literature Review / 2403.06910 / ISBN:https://doi.org/10.48550/arXiv.2403.06910 / Published by ArXiv / on (web) Publishing site
- 3. Analysis
References - Towards a Privacy and Security-Aware Framework for Ethical AI: Guiding the Development and Assessment of AI Systems / 2403.08624 / ISBN:https://doi.org/10.48550/arXiv.2403.08624 / Published by ArXiv / on (web) Publishing site
- 4 Results of the Systematic Literature Review
- Trust in AI: Progress, Challenges, and Future Directions / 2403.14680 / ISBN:https://doi.org/10.48550/arXiv.2403.14680 / Published by ArXiv / on (web) Publishing site
- 3. Findings
5. Concluding Remarks and Future Directions
Reference - AI Ethics: A Bibliometric Analysis, Critical Issues, and Key Gaps / 2403.14681 / ISBN:https://doi.org/10.48550/arXiv.2403.14681 / Published by ArXiv / on (web) Publishing site
- AI Ethics Development Phases Based on Keyword Analysis
- The Journey to Trustworthy AI- Part 1 Pursuit of Pragmatic Frameworks / 2403.15457 / ISBN:https://doi.org/10.48550/arXiv.2403.15457 / Published by ArXiv / on (web) Publishing site
- 8 Implementation Framework
References - The Pursuit of Fairness in Artificial Intelligence Models A Survey / 2403.17333 / ISBN:https://doi.org/10.48550/arXiv.2403.17333 / Published by ArXiv / on (web) Publishing site
- 5 Ways to mitigate bias and promote Fairness
8 Conclusion
References - AI Act and Large Language Models (LLMs): When critical issues and privacy impact require human and ethical oversight / 2404.00600 / ISBN:https://doi.org/10.48550/arXiv.2404.00600 / Published by ArXiv / on (web) Publishing site
- 6. Large Language Models (LLMs) - Introduction
- Exploring the Nexus of Large Language Models and Legal Systems: A Short Survey / 2404.00990 / ISBN:https://doi.org/10.48550/arXiv.2404.00990 / Published by ArXiv / on (web) Publishing site
- 4 Legal Problems of Large Languge Models
- The Pursuit of Fairness in Artificial Intelligence Models A Survey / 2403.17333 / ISBN:https://doi.org/10.48550/arXiv.2403.17333 / Published by ArXiv / on (web) Publishing site
- A Appendices
- A Critical Survey on Fairness Benefits of Explainable AI / 2310.13007 / ISBN:https://doi.org/10.1145/3630106.3658990 / Published by ArXiv / on (web) Publishing site
- 4 Critical Survey
5 Three Patterns of Critique
References
A Methodologies of Surveyed Literature - AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
2 Learning from Feedback
3 Learning under Distribution Shift
4 Assurance
5 Governance
6 Conclusion
References - Detecting AI Generated Text Based on NLP and Machine Learning Approaches / 2404.10032 / ISBN:https://doi.org/10.48550/arXiv.2404.10032 / Published by ArXiv / on (web) Publishing site
- I. Introduction
- Taxonomy to Regulation: A (Geo)Political Taxonomy for AI Risks and Regulatory Measures in the EU AI Act / 2404.11476 / ISBN:https://doi.org/10.48550/arXiv.2404.11476 / Published by ArXiv / on (web) Publishing site
- 4 European Union Artificial Intelligence Act
- Large Language Model Supply Chain: A Research Agenda / 2404.12736 / ISBN:https://doi.org/10.48550/arXiv.2404.12736 / Published by ArXiv / on (web) Publishing site
- 4 LLM Lifecycle
References - The Necessity of AI Audit Standards Boards / 2404.13060 / ISBN:https://doi.org/10.48550/arXiv.2404.13060 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
3 3 Governance for safety
References - From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap / 2404.13131 / ISBN:https://doi.org/10.1145/3630106.3658951 / Published by ArXiv / on (web) Publishing site
- References
- A Practical Multilevel Governance Framework for Autonomous and Intelligent Systems / 2404.13719 / ISBN:https://doi.org/10.48550/arXiv.2404.13719 / Published by ArXiv / on (web) Publishing site
- References
- Fairness in AI: challenges in bridging the gap between algorithms and law / 2404.19371 / ISBN:https://doi.org/10.48550/arXiv.2404.19371 / Published by ArXiv / on (web) Publishing site
- IV. Criteria for the Selection of Fairness Methods
- A Survey on Large Language Models for Critical Societal Domains: Finance, Healthcare, and Law / 2405.01769 / ISBN:https://doi.org/10.48550/arXiv.2405.01769 / Published by ArXiv / on (web) Publishing site
- 6 Ethics
References - Responsible AI: Portraits with Intelligent Bibliometrics / 2405.02846 / ISBN:https://doi.org/10.48550/arXiv.2405.02846 / Published by ArXiv / on (web) Publishing site
- II. Conceptualization: Responsible AI
IV. Bibliometric Portraits of Responsible AI
References - Trustworthy AI-Generative Content in Intelligent 6G Network: Adversarial, Privacy, and Fairness / 2405.05930 / ISBN:https://doi.org/10.48550/arXiv.2405.05930 / Published by ArXiv / on (web) Publishing site
- Abstract
I. Introduction
II. Trustworthy AIGC in 6G Network
IV. Privacy of AIGC in 6G Network
VI. Case Study
VII. Challenges and Future Research Directions
VIII. Conclusion - RAI Guidelines: Method for Generating Responsible AI Guidelines Grounded in Regulations and Usable by (Non-)Technical Roles / 2307.15158 / ISBN:https://doi.org/10.48550/arXiv.2307.15158 / Published by ArXiv / on (web) Publishing site
- 4 Method for Generating Responsible AI Guidelines
- Not My Voice! A Taxonomy of Ethical and Safety Harms of Speech Generators / 2402.01708 / ISBN:https://doi.org/10.48550/arXiv.2402.01708 / Published by ArXiv / on (web) Publishing site
- References
- The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative / 2402.14859 / ISBN:https://doi.org/10.48550/arXiv.2402.14859 / Published by ArXiv / on (web) Publishing site
- 2. Related Work
3. Methodology
4. Experiments
References - Integrating Emotional and Linguistic Models for Ethical Compliance in Large Language Models / 2405.07076 / ISBN:https://doi.org/10.48550/arXiv.2405.07076 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
3 Quantitative Models of Emotions, Behaviors, and Ethics
4 Pilot Studies
5 Conclusion
Appendix S: Multiple Adversarial LLMs - When AI Eats Itself: On the Caveats of Data Pollution in the Era of Generative AI / 2405.09597 / ISBN:https://doi.org/10.48550/arXiv.2405.09597 / Published by ArXiv / on (web) Publishing site
- 3 RQ2: What Technical Strategies Can Be
Employed to Mitigate the Negative Consequences
of AI Autophagy?
- The Narrow Depth and Breadth of Corporate Responsible AI Research / 2405.12193 / ISBN:https://doi.org/10.48550/arXiv.2405.12193 / Published by ArXiv / on (web) Publishing site
- S1 Additional Analyses on Engagement Analysis
- Pragmatic auditing: a pilot-driven approach for auditing Machine Learning systems / 2405.13191 / ISBN:https://doi.org/10.48550/arXiv.2405.13191 / Published by ArXiv / on (web) Publishing site
- 4 Conducting the Pilots
5 Lessons Learned from the Pilots - A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions / 2405.14487 / ISBN:https://doi.org/10.48550/arXiv.2405.14487 / Published by ArXiv / on (web) Publishing site
- I. Introduction
IV. Network Security
V. Privacy Preservation
VII. Cyber Security Operations Automation
VIII. Ethical LLMs
IX. Challenges and Open Problems
References - Towards Clinical AI Fairness: Filling Gaps in the Puzzle / 2405.17921 / ISBN:https://doi.org/10.48550/arXiv.2405.17921 / Published by ArXiv / on (web) Publishing site
- Methods in clinical AI fairness research
Reference
Additional material - Using Large Language Models for Humanitarian Frontline Negotiation: Opportunities and Considerations / 2405.20195 / ISBN:https://doi.org/10.48550/arXiv.2405.20195 / Published by ArXiv / on (web) Publishing site
- 1. Introduction
- Responsible AI for Earth Observation / 2405.20868 / ISBN:https://doi.org/10.48550/arXiv.2405.20868 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
3 Secure AI in EO: Focusing on Defense Mechanisms, Uncertainty Modeling and Explainability
References - Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models / 2406.05602 / Published by ArXiv / on (web) Publishing site
- References
- Deception Analysis with Artificial Intelligence: An Interdisciplinary Perspective / 2406.05724 / ISBN:https://doi.org/10.48550/arXiv.2406.05724 / Published by ArXiv / on (web) Publishing site
- References
- Federated Learning driven Large Language Models for Swarm Intelligence: A Survey / 2406.09831 / ISBN:https://doi.org/10.48550/arXiv.2406.09831 / Published by ArXiv / on (web) Publishing site
- III. Federated LLMs for Smarm Intelligence
IV. Learned Lessons and Open Challenges - Applications of Generative AI in Healthcare: algorithmic, ethical, legal and societal considerations / 2406.10632 / ISBN:https://doi.org/10.48550/arXiv.2406.10632 / Published by ArXiv / on (web) Publishing site
- III. Analysis
- Current state of LLM Risks and AI Guardrails / 2406.12934 / ISBN:https://doi.org/10.48550/arXiv.2406.12934 / Published by ArXiv / on (web) Publishing site
- 3 Strategies in Securing Large Language
models
References - AI Alignment through Reinforcement Learning from Human Feedback? Contradictions and Limitations / 2406.18346 / ISBN:https://doi.org/10.48550/arXiv.2406.18346 / Published by ArXiv / on (web) Publishing site
- 2 Background
- A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics / 2406.18812 / ISBN:https://doi.org/10.48550/arXiv.2406.18812 / Published by ArXiv / on (web) Publishing site
- I. INTRODUCTION AND MOTIVATION
III. ATTACKS ON DT-INTEGRATED AI ROBOTS
IV. DT-INTEGRATED ROBOTICS DESIGN CONSIDERATIONS AND DISCUSSION
REFERENCES - Staying vigilant in the Age of AI: From content generation to content authentication / 2407.00922 / ISBN:https://doi.org/10.48550/arXiv.2407.00922 / Published by ArXiv / on (web) Publishing site
- Emphasizing Reasoning Over Detection
References - SecGenAI: Enhancing Security of Cloud-based Generative AI Applications within Australian Critical Technologies of National Interest / 2407.01110 / ISBN:https://doi.org/10.48550/arXiv.2407.01110 / Published by ArXiv / on (web) Publishing site
- Abstract
II. UNDERSTANDING GENAI SECURITY
III. CRITICAL ANALYSIS
IV. SECGENAI FRAMEWORK REQUIREMENTS SPECIFICATIONS
REFERENCES - A Blueprint for Auditing Generative AI / 2407.05338 / ISBN:https://doi.org/10.48550/arXiv.2407.05338 / Published by ArXiv / on (web) Publishing site
- 4 Governance audits
5 Model audits
Bibliography - Auditing of AI: Legal, Ethical and Technical Approaches / 2407.06235 / Published by ArXiv / on (web) Publishing site
- 2 The evolution of auditing as a governance mechanism
4 Auditing of AI’s multidisciplinary foundations - Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models / 2310.19917 / ISBN:https://doi.org/10.48550/arXiv.2310.19917 / Published by ArXiv / on (web) Publishing site
- References
- FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare / 2309.12325 / ISBN:https://doi.org/10.48550/arXiv.2309.12325 / Published by ArXiv / on (web) Publishing site
- REFERENCES:
- Bridging the Global Divide in AI Regulation: A Proposal for a Contextual, Coherent, and Commensurable Framework / 2303.11196 / ISBN:https://doi.org/10.48550/arXiv.2303.11196 / Published by ArXiv / on (web) Publishing site
- I. Introduction
IV. Proposing an Alternative 3C Framework - Generative AI for Health Technology Assessment: Opportunities, Challenges, and Policy Considerations / 2407.11054 / ISBN:https://doi.org/10.48550/arXiv.2407.11054 / Published by ArXiv / on (web) Publishing site
- Limitations of generative AI in HTA applications
- Thorns and Algorithms: Navigating Generative AI Challenges Inspired by Giraffes and Acacias / 2407.11360 / ISBN:https://doi.org/10.48550/arXiv.2407.11360 / Published by ArXiv / on (web) Publishing site
- 4 Generative AI and Humans: Risks and Mitigation
- Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models / 2407.13059 / ISBN:https://doi.org/10.48550/arXiv.2407.13059 / Published by ArXiv / on (web) Publishing site
- Introduction
- Assurance of AI Systems From a Dependability Perspective / 2407.13948 / ISBN:https://doi.org/10.48550/arXiv.2407.13948 / Published by ArXiv / on (web) Publishing site
- 2 Assurance for Systems Extended with AI and ML
4 Assurance for General-Purpose AI
5 Assurance and Alignment for AGI
References - Open Artificial Knowledge / 2407.14371 / ISBN:https://doi.org/10.48550/arXiv.2407.14371 / Published by ArXiv / on (web) Publishing site
- References
- RogueGPT: dis-ethical tuning transforms ChatGPT4 into a Rogue AI in 158 Words / 2407.15009 / ISBN:https://doi.org/10.48550/arXiv.2407.15009 / Published by ArXiv / on (web) Publishing site
- I. Introduction
II. Background
III. Methodology
References - Mapping the individual, social, and biospheric impacts of Foundation Models / 2407.17129 / ISBN:https://doi.org/10.48550/arXiv.2407.17129 / Published by ArXiv / on (web) Publishing site
- References
- Deepfake Media Forensics: State of the Art and Challenges Ahead / 2408.00388 / ISBN:https://doi.org/10.48550/arXiv.2408.00388 / Published by ArXiv / on (web) Publishing site
- Abstract
5. Deepfakes Detection Method on Realistic Scenarios
References - Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity / 2408.04023 / ISBN:https://doi.org/10.48550/arXiv.2408.04023 / Published by ArXiv / on (web) Publishing site
- 2. Related Work
3. Proposed framework
7. Conclusion and Future Directions - The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources / 2406.16746 / ISBN:https://doi.org/10.48550/arXiv.2406.16746 / Published by ArXiv / on (web) Publishing site
- 8 Model Evaluation
9 Model Release & Monitoring
References - Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives / 2407.14962 / ISBN:https://doi.org/10.48550/arXiv.2407.14962 / Published by ArXiv / on (web) Publishing site
- I. Introduction
II. Generative AI
IV. Challenges of Generative AI and LLMs
References - VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary / 2407.19524 / ISBN:https://doi.org/10.48550/arXiv.2407.19524 / Published by ArXiv / on (web) Publishing site
- References
- Neuro-Symbolic AI for Military Applications / 2408.09224 / ISBN:https://doi.org/10.48550/arXiv.2408.09224 / Published by ArXiv / on (web) Publishing site
- I. Introduction
V. Challenges and Risks
References - CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher / 2408.11650 / ISBN:https://doi.org/10.48550/arXiv.2408.11650 / Published by ArXiv / on (web) Publishing site
- 4. Experiment Results
References - Promises and challenges of generative artificial intelligence for human learning / 2408.12143 / ISBN:https://doi.org/10.48550/arXiv.2408.12143 / Published by ArXiv / on (web) Publishing site
- 2 Promises
3 Challenges - Catalog of General Ethical Requirements for AI Certification / 2408.12289 / ISBN:https://doi.org/10.48550/arXiv.2408.12289 / Published by ArXiv / on (web) Publishing site
- 6 Fairness (F)
8 Safety and Robustness (SR)
11 Truthfulness (TR) - Is Generative AI the Next Tactical Cyber Weapon For Threat Actors? Unforeseen Implications of AI Generated Cyber Attacks / 2408.12806 / ISBN:https://doi.org/10.48550/arXiv.2408.12806 / Published by ArXiv / on (web) Publishing site
- III. Generative AI
References - Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey / 2408.12880 / ISBN:https://doi.org/10.48550/arXiv.2408.12880 / Published by ArXiv / on (web) Publishing site
- 3 Multimodal Medical Studies
References - Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems / 2408.15550 / ISBN:https://doi.org/10.48550/arXiv.2408.15550 / Published by ArXiv / on (web) Publishing site
- 3 Governance for Human-Centric Intelligence
Systems
- Digital Homunculi: Reimagining Democracy Research with Generative Agents / 2409.00826 / ISBN:https://doi.org/10.48550/arXiv.2409.00826 / Published by ArXiv / on (web) Publishing site
- 5. Annoyances or Dealbreakers?
- DetoxBench: Benchmarking Large Language Models for Multitask Fraud & Abuse Detection / 2409.06072 / ISBN:https://doi.org/10.48550/arXiv.2409.06072 / Published by ArXiv / on (web) Publishing site
- 2 Prior Benchmarks
References - Catalog of General Ethical Requirements for AI Certification / 2408.12289 / ISBN:https://doi.org/10.48550/arXiv.2408.12289 / Published by ArXiv / on (web) Publishing site
- References
- The overlooked need for Ethics in Complexity Science: Why it matters / 2409.02002 / ISBN:https://doi.org/10.48550/arXiv.2409.02002 / Published by ArXiv / on (web) Publishing site
- Annexus
- On the Creativity of Large Language Models / 2304.00008 / ISBN:https://doi.org/10.48550/arXiv.2304.00008 / Published by ArXiv / on (web) Publishing site
- 2 A Creative Journey from Ada Lovelace to Foundation Models
References - Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward / 2305.08413 / ISBN:https://doi.org/10.48550/arXiv.2305.08413 / Published by ArXiv / on (web) Publishing site
- 7 Earth observation and society: the growing relevance of ethics
References - Views on AI aren't binary -- they're plural / 2312.14230 / ISBN:https://doi.org/10.48550/arXiv.2312.14230 / Published by ArXiv / on (web) Publishing site
- Overcoming the dichotomy: How to build bridges
References - Data-Centric Foundation Models in Computational Healthcare: A Survey / 2401.02458 / ISBN:https://doi.org/10.48550/arXiv.2401.02458 / Published by ArXiv / on (web) Publishing site
- 9 Challenges and Opportunities
- Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models / 2401.16727 / ISBN:https://doi.org/10.48550/arXiv.2401.16727 / Published by ArXiv / on (web) Publishing site
- 2 Hate Speech
3 Methodology
References - Navigating LLM Ethics: Advancements, Challenges, and Future Directions / 2406.18841 / ISBN:https://doi.org/10.48550/arXiv.2406.18841 / Published by ArXiv / on (web) Publishing site
- IV. Findings and Resultant Themes
References - GenAI Advertising: Risks of Personalizing Ads with LLMs / 2409.15436 / ISBN:https://doi.org/10.48550/arXiv.2409.15436 / Published by ArXiv / on (web) Publishing site
- 4 Effects of Ad Injection on LLM Performance
A Appendix - XTRUST: On the Multilingual Trustworthiness of Large Language Models / 2409.15762 / ISBN:https://doi.org/10.48550/arXiv.2409.15762 / Published by ArXiv / on (web) Publishing site
- 4 Experiments
- Artificial Human Intelligence: The role of Humans in the Development of Next Generation AI / 2409.16001 / ISBN:https://doi.org/10.48550/arXiv.2409.16001 / Published by ArXiv / on (web) Publishing site
- 5 Challenges and Perspectives in Human-Level AI Development
References - Decoding Large-Language Models: A Systematic Overview of Socio-Technical Impacts, Constraints, and Emerging Questions / 2409.16974 / ISBN:https://doi.org/10.48550/arXiv.2409.16974 / Published by ArXiv / on (web) Publishing site
- 5 Aims & Objectives (RQ1)
6 Methodologies & Capabilities (RQ2) - Social Media Bot Policies: Evaluating Passive and Active Enforcement / 2409.18931 / ISBN:https://doi.org/10.48550/arXiv.2409.18931 / Published by ArXiv / on (web) Publishing site
- II. Related Work
- Responsible AI in Open Ecosystems: Reconciling Innovation with Risk Assessment and Disclosure / 2409.19104 / ISBN:https://doi.org/10.48550/arXiv.2409.19104 / Published by ArXiv / on (web) Publishing site
- 2 Related Work
3 Methods
References
A Benchmarks in Open LLM Leaderboard - Ethical software requirements from user reviews: A systematic literature review / 2410.01833 / ISBN:https://doi.org/10.48550/arXiv.2410.01833 / Published by ArXiv / on (web) Publishing site
- IV. Results
References - From human-centered to social-centered artificial intelligence: Assessing ChatGPT's impact through disruptive events / 2306.00227 / ISBN:https://doi.org/10.48550/arXiv.2306.00227 / Published by ArXiv / on (web) Publishing site
- The multiple levels of AI impact
- Trust or Bust: Ensuring Trustworthiness in Autonomous Weapon Systems / 2410.10284 / ISBN:https://doi.org/10.48550/arXiv.2410.10284 / Published by ArXiv / on (web) Publishing site
- I. Introduction
- When AI Eats Itself: On the Caveats of Data Pollution in the Era of Generative AI / 2405.09597 / ISBN:https://doi.org/10.48550/arXiv.2405.09597 / Published by ArXiv / on (web) Publishing site
- References
- Navigating the Cultural Kaleidoscope: A Hitchhiker's Guide to Sensitivity in Large Language Models / 2410.12880 / ISBN:https://doi.org/10.48550/arXiv.2410.12880 / Published by ArXiv / on (web) Publishing site
- 6 Main results on evaluation set
- How Do AI Companies Fine-Tune Policy? Examining Regulatory Capture in AI Governance / 2410.13042 / ISBN:https://doi.org/10.48550/arXiv.2410.13042 / Published by ArXiv / on (web) Publishing site
- References
- Data Defenses Against Large Language Models / 2410.13138 / ISBN:https://doi.org/10.48550/arXiv.2410.13138 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
4 LLM Adversarial Attacks as LLM Inference Data Defenses
7 Conclusion and Limitations
References
Appendices - Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems / 2410.13334 / ISBN:https://doi.org/10.48550/arXiv.2410.13334 / Published by ArXiv / on (web) Publishing site
- 1 Introduction
2 Background and Related Works
Refefences - Confrontation or Acceptance: Understanding Novice Visual Artists' Perception towards AI-assisted Art Creation / 2410.14925 / ISBN:https://doi.org/10.48550/arXiv.2410.14925 / Published by ArXiv / on (web) Publishing site
- References
- Jailbreaking and Mitigation of Vulnerabilities in Large Language Models / 2410.15236 / ISBN:https://doi.org/10.48550/arXiv.2410.15236 / Published by ArXiv / on (web) Publishing site
- Abstract
I. Introduction
II. Background and Concepts
III. Jailbreak Attack Methods and Techniques
IV. Defense Mechanisms Against Jailbreak Attacks
V. Evaluation and Benchmarking
VI. Research Gaps and Future Directions
VII. Conclusion
References - Trustworthy XAI and Application / 2410.17139 / ISBN:https://doi.org/10.48550/arXiv.2410.17139 / Published by ArXiv / on (web) Publishing site
- 3 Applications of Trustworthy XAI
References - The Cat and Mouse Game: The Ongoing Arms Race Between Diffusion Models and Detection Methods / 2410.18866 / ISBN:https://doi.org/10.48550/arXiv.2410.18866 / Published by ArXiv / on (web) Publishing site
- Abstract
VI. Evaluation Metrics
VIII. Research Gaps and Future Directions
References - TRIAGE: Ethical Benchmarking of AI Models Through Mass Casualty Simulations / 2410.18991 / ISBN:https://doi.org/10.48550/arXiv.2410.18991 / Published by ArXiv / on (web) Publishing site
- Abstract
1 Introduction
3 Results - Standardization Trends on Safety and Trustworthiness Technology for Advanced AI / 2410.22151 / ISBN:https://doi.org/10.48550/arXiv.2410.22151 / Published by ArXiv / on (web) Publishing site
- 3 Trends in advanced AI safety and trustworthiness standardization
References