Why_this_webapp Bibliography

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

5 Falsification and Evaluation

Getting pwn'd by AI: Penetration Testing with Large Language Models / 2308.00121 / ISBN:https://doi.org/10.48550/arXiv.2308.00121 / Published by ArXiv / on (web) Publishing site

3 LLM-based penetration testing
6 Final ethical considerations

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
4 Experiments

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

IV. Attack Surfaces

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

1 Introduction
3 Methodology

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

Ethical Considerations Towards Protestware / 2306.10019 / ISBN:https://doi.org/10.48550/arXiv.2306.10019 / Published by ArXiv / on (web) Publishing site

Abstract
II. Background
III. Ethics: a primer

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

Abstract
3 Control the Risks of AI Models in Science
Appendix D Details of Benchmark Results

Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence / 2402.08466 / ISBN:https://doi.org/10.48550/arXiv.2402.08466 / Published by ArXiv / on (web) Publishing site

2 Emerging Management-based AI Regulation

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

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

IV. Challenges and Considerations

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

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

AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / on (web) Publishing site

1 Introduction
2 Learning from Feedback
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

3. Methodology
4. Experiments

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

3 Limitations of RLxF

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

6 Discussion

Nudging Using Autonomous Agents: Risks and Ethical Considerations / 2407.16362 / ISBN:https://doi.org/10.48550/arXiv.2407.16362 / Published by ArXiv / on (web) Publishing site

4 Ethical Considerations
5 Principles for the Nudge Lifecycle

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

5. Deepfakes Detection Method on Realistic Scenarios
6. Active Authentication

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

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

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

IV. Attack Methodology

AI Governance in Higher Education: Case Studies of Guidance at Big Ten Universities / 2409.02017 / ISBN:https://doi.org/10.48550/arXiv.2409.02017 / Published by ArXiv / on (web) Publishing site

References

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

5 Future Directions

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
Appendices

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

I. Introduction
V. Results

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

4 Cultural safety dataset

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

4 Experiment
A Appendix

A Simulation System Towards Solving Societal-Scale Manipulation / 2410.13915 / ISBN:https://doi.org/10.48550/arXiv.2410.13915 / Published by ArXiv / on (web) Publishing site

Appendices

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

I. Introduction
II. Background and Concepts
III. Jailbreak Attack Methods and Techniques
IV. Defense Mechanisms Against Jailbreak Attacks
V. Evaluation and Benchmarking
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

The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationships / 2410.20130 / ISBN:https://doi.org/10.48550/arXiv.2410.20130 / Published by ArXiv / on (web) Publishing site

4 Results

The doctor will polygraph you now: ethical concerns with AI for fact-checking patients / 2408.07896 / ISBN:https://doi.org/10.48550/arXiv.2408.07896 / Published by ArXiv / on (web) Publishing site

3. Methods

Examining Multimodal Gender and Content Bias in ChatGPT-4o / 2411.19140 / ISBN:https://doi.org/10.48550/arXiv.2411.19140 / Published by ArXiv / on (web) Publishing site

2. Related Works

Large Language Models in Politics and Democracy: A Comprehensive Survey / 2412.04498 / ISBN:https://doi.org/10.48550/arXiv.2412.04498 / Published by ArXiv / on (web) Publishing site

References

AI Ethics in Smart Homes: Progress, User Requirements and Challenges / 2412.09813 / ISBN:https://doi.org/10.48550/arXiv.2412.09813 / Published by ArXiv / on (web) Publishing site

5 AI Ethics from Technology's Perspective

Clio: Privacy-Preserving Insights into Real-World AI Use / 2412.13678 / ISBN:https://doi.org/10.48550/arXiv.2412.13678 / Published by ArXiv / on (web) Publishing site

4 Clio for safety
Appendices

Towards Friendly AI: A Comprehensive Review and New Perspectives on Human-AI Alignment / 2412.15114 / ISBN:https://doi.org/10.48550/arXiv.2412.15114 / Published by ArXiv / on (web) Publishing site

II. Friendly AI Definition

Large Language Model Safety: A Holistic Survey / 2412.17686 / ISBN:https://doi.org/10.48550/arXiv.2412.17686 / Published by ArXiv / on (web) Publishing site

5 Misuse

Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s) / 2501.11705 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s)

FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing / 2502.03826 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

References

Safety at Scale: A Comprehensive Survey of Large Model Safety / 2502.05206 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

2 Vision Foundation Model Safety
3 Large Language Model Safety
5 Vision-Language Model Safety
7 Agent Safety
8 Open Challenges

The Odyssey of the Fittest: Can Agents Survive and Still Be Good? / 2502.05442 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

Introduction

Position: We Need An Adaptive Interpretation of Helpful, Honest, and Harmless Principles / 2502.06059 / ISBN:https://doi.org/10.48550/arXiv. / Published by ArXiv / on (web) Publishing site

3 Ambiguity and Conflicts in HHH

Multi-Agent Risks from Advanced AI / 2502.14143 / ISBN:https://doi.org/10.48550/arXiv.2502.14143 / Published by ArXiv / on (web) Publishing site

3 Risk Factors

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective / 2502.14296 / ISBN:https://doi.org/10.48550/arXiv.2502.14296 / Published by ArXiv / on (web) Publishing site

1 Introduction
5 Benchmarking Text-to-Image Models
6 Benchmarking Large Language Models
7 Benchmarking Vision-Language Models
8 Other Generative Models
9 Trustworthiness in Downstream Applications
10 Further Discussion
References

Transforming Cyber Defense: Harnessing Agentic and Frontier AI for Proactive, Ethical Threat Intelligence / 2503.00164 / ISBN:https://doi.org/10.48550/arXiv.2503.00164 / Published by ArXiv / on (web) Publishing site

4 Agentic AI and Frontier AI in Cybersecu- rity

Medical Hallucinations in Foundation Models and Their Impact on Healthcare / 2503.05777 / ISBN:https://doi.org/10.48550/arXiv.2503.05777 / Published by ArXiv / on (web) Publishing site

2 LLM Hallucinations in Medicine

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective / 2502.14296 / ISBN:https://doi.org/10.48550/arXiv.2502.14296 / Published by ArXiv / on (web) Publishing site

Appendices