_
RobertoLofaro.com - Knowledge Portal - human-generated content
Change, with and without technology
for updates on publications, follow @robertolofaro on Instagram or @changerulebook on Twitter, you can also support on Patreon or subscribe on YouTube


_

You are now here: AI Ethics Primer - search within the bibliography - version 0.4 of 2023-12-13 > (tag cloud) >tag_selected: unsafe


Currently searching for:

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: unsafe

Bibliography items where occurs: 44
The AI Index 2022 Annual Report / 2205.03468 / ISBN:https://doi.org/10.48550/arXiv.2205.03468 / Published by ArXiv / on (web) Publishing site
Appendix


The Ethics of AI Value Chains / 2307.16787 / ISBN:https://doi.org/10.48550/arXiv.2307.16787 / Published by ArXiv / on (web) Publishing site
4. Ethical Implications of AI Value Chains


Bad, mad, and cooked: Moral responsibility for civilian harms in human-AI military teams / 2211.06326 / ISBN:https://doi.org/10.48550/arXiv.2211.06326 / Published by ArXiv / on (web) Publishing site
AI Workplace Health and Safety Framework


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
3 Vulnerabilities, Attack, and Limitations


Building Trust in Conversational AI: A Comprehensive Review and Solution Architecture for Explainable, Privacy-Aware Systems using LLMs and Knowledge Graph / 2308.13534 / ISBN:https://doi.org/10.48550/arXiv.2308.13534 / Published by ArXiv / on (web) Publishing site
IV. Applied and technology implications for LLMs


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
3 Emerging dual-use risks and vulnerabilities in AI systems


The AI Incident Database as an Educational Tool to Raise Awareness of AI Harms: A Classroom Exploration of Efficacy, Limitations, & Future Improvements / 2310.06269 / ISBN:https://doi.org/10.48550/arXiv.2310.06269 / Published by ArXiv / on (web) Publishing site
1 Introduction


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
I Responses on Prompts from PALMS, LaMDA, and InstructGPT


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
Abstract
3 ReFLeCT: Robust, Fair, and Safe LLM Construction Test Suite
4 Empirical Evaluation and Outcomes


Ethical Implications of ChatGPT in Higher Education: A Scoping Review / 2311.14378 / ISBN:https://doi.org/10.48550/arXiv.2311.14378 / Published by ArXiv / on (web) Publishing site
Research Method


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


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
3 Control the Risks of AI Models in Science
4 Call for Responsible AI for Science


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


Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence / 2402.09880 / ISBN:https://doi.org/10.48550/arXiv.2402.09880 / Published by ArXiv / on (web) Publishing site
I. Introduction


Moral Sparks in Social Media Narratives / 2310.19268 / ISBN:https://doi.org/10.48550/arXiv.2310.19268 / Published by ArXiv / on (web) Publishing site
5. Results


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


Analyzing Potential Solutions Involving Regulation to Escape Some of AI's Ethical Concerns / 2403.15507 / ISBN:https://doi.org/10.48550/arXiv.2403.15507 / Published by ArXiv / on (web) Publishing site
Feasibility of Government Regulation


Designing for Human-Agent Alignment: Understanding what humans want from their agents / 2404.04289 / ISBN:https://doi.org/10.1145/3613905.3650948 / Published by ArXiv / on (web) Publishing site
4 Findings


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


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
3 A Geo-Political AI Risk Taxonomy


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
3 3 Governance for safety


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
VI. Case Study


Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback / 2404.10271 / ISBN:https://doi.org/10.48550/arXiv.2404.10271 / Published by ArXiv / on (web) Publishing site
Abstract


The Future of Child Development in the AI Era. Cross-Disciplinary Perspectives Between AI and Child Development Experts / 2405.19275 / ISBN:https://doi.org/10.48550/arXiv.2405.19275 / Published by ArXiv / on (web) Publishing site
2. Anticipated AI Use for Children


The Ethics of Interaction: Mitigating Security Threats in LLMs / 2401.12273 / ISBN:https://doi.org/10.48550/arXiv.2401.12273 / Published by ArXiv / on (web) Publishing site
1 Introduction


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
2 Large Language Model Risks


A Blueprint for Auditing Generative AI / 2407.05338 / ISBN:https://doi.org/10.48550/arXiv.2407.05338 / Published by ArXiv / on (web) Publishing site
2 Why audit generative AI systems?


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


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


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
References


Integrating ESG and AI: A Comprehensive Responsible AI Assessment Framework / 2408.00965 / ISBN:https://doi.org/10.48550/arXiv.2408.00965 / Published by ArXiv / on (web) Publishing site
2 Background and Literature Review
4 ESG-AI framework


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
3 XTRUST Construction


Safety challenges of AI in medicine / 2409.18968 / ISBN:https://doi.org/10.48550/arXiv.2409.18968 / Published by ArXiv / on (web) Publishing site
2 Inherent problems of AI related to medicine
3 Risks of using AI in medicine


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
APPENDIX D ADDITIONAL INFORMATION


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
8 Results after cultural safeguarding


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
1 Introduction
8 Conclusion


Data Defenses Against Large Language Models / 2410.13138 / ISBN:https://doi.org/10.48550/arXiv.2410.13138 / Published by ArXiv / on (web) Publishing site
4 LLM Adversarial Attacks as LLM Inference Data Defenses
5 Experiments
8 Ethics Considerations and Compliance with the Open Science Policy


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
III. Jailbreak Attack Methods and Techniques
V. Evaluation and Benchmarking


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
Appendices


Framework for developing and evaluating ethical collaboration between expert and machine / 2411.10983 / ISBN:https://doi.org/10.48550/arXiv.2411.10983 / Published by ArXiv / on (web) Publishing site
2. Method


Ethical Challenges and Evolving Strategies in the Integration of Artificial Intelligence into Clinical Practice / 2412.03576 / ISBN:https://doi.org/10.48550/arXiv.2412.03576 / Published by ArXiv / on (web) Publishing site
Introduction and Motivation
Core Ethical Challenges


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
III. Theoretical Perspectives


Autonomous Vehicle Security: A Deep Dive into Threat Modeling / 2412.15348 / ISBN:https://doi.org/10.48550/arXiv.2412.15348 / Published by ArXiv / on (web) Publishing site
III. Autonomous Vehicle Cybersecurirty Attacks


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
1 Introduction
2 Taxonomy
3 Value Misalignment
4 Robustness to Attack
7 Agent Safety
8 Interpretability for LLM Safety
9 Technology Roadmaps / Strategies to LLM Safety in Practice
11 Challenges and Future Directions
References


Implications of Artificial Intelligence on Health Data Privacy and Confidentiality / 2501.01639 / ISBN:https://doi.org/10.48550/arXiv.2501.01639 / Published by ArXiv / on (web) Publishing site
Cases and Examples