_
RobertoLofaro.com - Knowledge Portal - human-generated content
Change, with and without technology - human, AI, scraping readers welcome
for updates on publications, follow: on Instagram, Twitter, Patreon, YouTube


_

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


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: benign

Bibliography items where occurs: 76
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 / Version released on 2023-08-27 / on (web) Publishing site


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 / Version released on 2023-08-17 / on (web) Publishing site


Targeted Data Augmentation for bias mitigation / 2308.11386 / ISBN:https://doi.org/10.48550/arXiv.2308.11386 / Published by ArXiv / Version released on 2023-08-22 / on (web) Publishing site


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 / Version released on 2024-01-26 / on (web) Publishing site


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 / Version released on 2024-04-02 / on (web) Publishing site


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 / Version released on 2023-11-29 / on (web) Publishing site


Ethical Considerations Towards Protestware / 2306.10019 / ISBN:https://doi.org/10.48550/arXiv.2306.10019 / Published by ArXiv / Version released on 2024-01-05 / on (web) Publishing site


Control Risk for Potential Misuse of Artificial Intelligence in Science / 2312.06632 / ISBN:https://doi.org/10.48550/arXiv.2312.06632 / Published by ArXiv / Version released on 2023-12-11 / on (web) Publishing site


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 / Version released on 2024-06-27 / on (web) Publishing site


User Modeling and User Profiling: A Comprehensive Survey / 2402.09660 / ISBN:https://doi.org/10.48550/arXiv.2402.09660 / Published by ArXiv / Version released on 2024-02-20 / on (web) Publishing site


Towards an AI-Enhanced Cyber Threat Intelligence Processing Pipeline / 2403.03265 / ISBN:https://doi.org/10.48550/arXiv.2403.03265 / Published by ArXiv / Version released on 2024-03-05 / on (web) Publishing site


Trust in AI: Progress, Challenges, and Future Directions / 2403.14680 / ISBN:https://doi.org/10.48550/arXiv.2403.14680 / Published by ArXiv / Version released on 2024-04-04 / on (web) Publishing site


AI Alignment: A Comprehensive Survey / 2310.19852 / ISBN:https://doi.org/10.48550/arXiv.2310.19852 / Published by ArXiv / Version released on 2025-04-04 / on (web) Publishing site


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 / Version released on 2024-06-03 / on (web) Publishing site


How Ethical Should AI Be? How AI Alignment Shapes the Risk Preferences of LLMs / 2406.01168 / ISBN:https://doi.org/10.48550/arXiv.2406.01168 / Published by ArXiv / Version released on 2024-08-01 / on (web) Publishing site


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 / Version released on 2024-06-26 / on (web) Publishing site


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 / Version released on 2024-07.16 / on (web) Publishing site


Nudging Using Autonomous Agents: Risks and Ethical Considerations / 2407.16362 / ISBN:https://doi.org/10.48550/arXiv.2407.16362 / Published by ArXiv / Version released on 2024-07-23 / on (web) Publishing site


Deepfake Media Forensics: State of the Art and Challenges Ahead / 2408.00388 / ISBN:https://doi.org/10.48550/arXiv.2408.00388 / Published by ArXiv / Version released on 2024-08-13 / on (web) Publishing site


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 / Version released on 2024-09-03 / on (web) Publishing site


CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher / 2408.11650 / ISBN:https://doi.org/10.48550/arXiv.2408.11650 / Published by ArXiv / Version released on 2024-11-06 / on (web) Publishing site


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 / Version released on 2024-08-23 / on (web) Publishing site


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 / Version released on 2024-10-30 / on (web) Publishing site


XTRUST: On the Multilingual Trustworthiness of Large Language Models / 2409.15762 / ISBN:https://doi.org/10.48550/arXiv.2409.15762 / Published by ArXiv / Version released on 2024-09-24 / on (web) Publishing site


Social Media Bot Policies: Evaluating Passive and Active Enforcement / 2409.18931 / ISBN:https://doi.org/10.48550/arXiv.2409.18931 / Published by ArXiv / Version released on 2024-09-27 / on (web) Publishing site


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 / Version released on 2025-01-24 / on (web) Publishing site


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 / Version released on 2024-10-23 / on (web) Publishing site


A Simulation System Towards Solving Societal-Scale Manipulation / 2410.13915 / ISBN:https://doi.org/10.48550/arXiv.2410.13915 / Published by ArXiv / Version released on 2024-10-17 / on (web) Publishing site


Jailbreaking and Mitigation of Vulnerabilities in Large Language Models / 2410.15236 / ISBN:https://doi.org/10.48550/arXiv.2410.15236 / Published by ArXiv / Version released on 2025-11-25 / on (web) Publishing site


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 / Version released on 2025-01-26 / on (web) Publishing site


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 / Version released on 2024-11-11 / on (web) Publishing site


Examining Multimodal Gender and Content Bias in ChatGPT-4o / 2411.19140 / ISBN:https://doi.org/10.48550/arXiv.2411.19140 / Published by ArXiv / Version released on 2024-11-28 / on (web) Publishing site


AI Ethics in Smart Homes: Progress, User Requirements and Challenges / 2412.09813 / ISBN:https://doi.org/10.48550/arXiv.2412.09813 / Published by ArXiv / Version released on 2024-12-13 / on (web) Publishing site


Clio: Privacy-Preserving Insights into Real-World AI Use / 2412.13678 / ISBN:https://doi.org/10.48550/arXiv.2412.13678 / Published by ArXiv / Version released on 2024-12-18 / on (web) Publishing site


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 / Version released on 2024-12-19 / on (web) Publishing site


Large Language Model Safety: A Holistic Survey / 2412.17686 / ISBN:https://doi.org/10.48550/arXiv.2412.17686 / Published by ArXiv / Version released on 2024-12-23 / on (web) Publishing site


Human services organizations and the responsible integration of AI: Considering ethics and contextualizing risk(s) / 2501.11705 / ISBN:https://doi.org/10.48550/arXiv.2501.11705 / Published by ArXiv / Version released on 2025-01-20 / on (web) Publishing site


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.2502.03826 / Published by ArXiv / Version released on 2025-08-15 / on (web) Publishing site


Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety / 2502.05206 / ISBN:https://doi.org/10.48550/arXiv.2502.05206 / Published by ArXiv / Version released on 2025-08-02 / on (web) Publishing site


The Odyssey of the Fittest: Can Agents Survive and Still Be Good? / 2502.05442 / ISBN:https://doi.org/10.48550/arXiv.2502.05442 / Published by ArXiv / Version released on 2025-07-15 / on (web) Publishing site


Prioritization First, Principles Second: An Adaptive Interpretation of Helpful, Honest, and Harmless Principles / 2502.06059 / ISBN:https://doi.org/10.48550/arXiv.2502.06059 / Published by ArXiv / Version released on 2025-12-27 / on (web) Publishing site


Multi-Agent Risks from Advanced AI / 2502.14143 / ISBN:https://doi.org/10.48550/arXiv.2502.14143 / Published by ArXiv / Version released on 2025-02-19 / on (web) Publishing site


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 / Version released on 2025-09-30 / on (web) Publishing site


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 / Version released on 2025-02-28 / on (web) Publishing site


Medical Hallucinations in Foundation Models and Their Impact on Healthcare / 2503.05777 / ISBN:https://doi.org/10.48550/arXiv.2503.05777 / Published by ArXiv / Version released on 2025-02-26 / on (web) Publishing site


Detecting Dataset Bias in Medical AI: A Generalized and Modality-Agnostic Auditing Framework / 2503.09969 / ISBN:https://doi.org/10.48550/arXiv.2503.09969 / Published by ArXiv / Version released on 2025-03-13 / on (web) Publishing site


MinorBench: A hand-built benchmark for content-based risks for children / 2503.10242 / ISBN:https://doi.org/10.48550/arXiv.2503.10242 / Published by ArXiv / Version released on 2025-03-13 / on (web) Publishing site


Gender and content bias in Large Language Models: a case study on Google Gemini 2.0 Flash Experimental / 2503.16534 / ISBN:https://doi.org/10.48550/arXiv.2503.16534 / Published by ArXiv / Version released on 2025-03-18 / on (web) Publishing site


Towards interactive evaluations for interaction harms in human-AI systems / 2405.10632 / ISBN:https://doi.org/10.48550/arXiv.2405.10632 / Published by ArXiv / Version released on 2025-07-30 / on (web) Publishing site


Confirmation Bias in Generative AI Chatbots: Mechanisms, Risks, Mitigation Strategies, and Future Research Directions / 2504.09343 / ISBN:https://doi.org/10.48550/arXiv.2504.09343 / Published by ArXiv / Version released on 2025-04-12 / on (web) Publishing site


From Texts to Shields: Convergence of Large Language Models and Cybersecurity / 2505.00841 / ISBN:https://doi.org/10.48550/arXiv.2505.00841 / Published by ArXiv / Version released on 2025-05-01 / on (web) Publishing site


Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs / 2505.02009 / ISBN:https://doi.org/10.48550/arXiv.2505.02009 / Published by ArXiv / Version released on 2025-08-12 / on (web) Publishing site


Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data / 2505.09974 / ISBN:https://doi.org/10.48550/arXiv.2505.09974 / Published by ArXiv / Version released on 2025-05-15 / on (web) Publishing site


SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents / 2505.23559 / ISBN:https://doi.org/10.48550/arXiv.2505.23559 / Published by ArXiv / Version released on 2025-05-29 / on (web) Publishing site


Locating Risk: Task Designers and the Challenge of Risk Disclosure in RAI Content Work / 2505.24246 / ISBN:https://doi.org/10.48550/arXiv.2505.24246 / Published by ArXiv / Version released on 2025-09-30 / on (web) Publishing site


Surgeons Awareness, Expectations, and Involvement with Artificial Intelligence: a Survey Pre and Post the GPT Era / 2506.08258 / ISBN:https://doi.org/10.48550/arXiv.2506.08258 / Published by ArXiv / Version released on 2025-06-09 / on (web) Publishing site


The Ethics of Generative AI in Anonymous Spaces: A Case Study of 4chan's /pol/ Board / 2506.14191 / ISBN:https://doi.org/10.48550/arXiv.2506.14191 / Published by ArXiv / Version released on 2025-06-17 / on (web) Publishing site


Mechanistic Interpretability Needs Philosophy / 2506.18852 / ISBN:https://doi.org/10.48550/arXiv.2506.18852 / Published by ArXiv / Version released on 2025-06-23 / on (web) Publishing site


On the Surprising Efficacy of LLMs for Penetration-Testing / 2507.00829 / ISBN:https://doi.org/10.48550/arXiv.2507.00829 / Published by ArXiv / Version released on 2025-07-01 / on (web) Publishing site


Exploiting Jailbreaking Vulnerabilities in Generative AI to Bypass Ethical Safeguards for Facilitating Phishing Attacks / 2507.12185 / ISBN:https://doi.org/10.48550/arXiv.2507.12185 / Published by ArXiv / Version released on 2025-07-16 / on (web) Publishing site


PRAC3 (Privacy, Reputation, Accountability, Consent, Credit, Compensation): Long Tailed Risks of Voice Actors in AI Data-Economy / 2507.16247 / ISBN:https://doi.org/10.48550/arXiv.2507.16247 / Published by ArXiv / Version released on 2025-07-22 / on (web) Publishing site


EthicAlly: a Prototype for AI-Powered Research Ethics Support for the Social Sciences and Humanities / 2508.00856 / ISBN:https://doi.org/10.48550/arXiv.2508.00856 / Published by ArXiv / Version released on 2025-07-15 / on (web) Publishing site


Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance / 2508.08789 / ISBN:https://doi.org/10.48550/arXiv.2508.08789 / Published by ArXiv / Version released on 2025-08-18 / on (web) Publishing site


The AI-Fraud Diamond: A Novel Lens for Auditing Algorithmic Deception / 2508.13984 / ISBN:https://doi.org/10.48550/arXiv.2508.13984 / Published by ArXiv / Version released on 2025-08-19 / on (web) Publishing site


Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs / 2509.05367 / ISBN:https://doi.org/10.48550/arXiv.2509.05367 / Published by ArXiv / Version released on 2025-09-12 / on (web) Publishing site


AI Governance in Higher Education: A course design exploring regulatory, ethical and practical considerationsAI Governance in Higher Education: A course design exploring regulatory, ethical and practical considerations / 2509.06176 / ISBN:https://doi.org/10.48550/arXiv.2509.06176 / Published by ArXiv / Version released on 2025-09-16 / on (web) Publishing site


The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs / 2506.11094 / ISBN:https://doi.org/10.48550/arXiv.2506.11094 / Published by ArXiv / Version released on 2025-10-30 / on (web) Publishing site


AI Alignment vs. AI Ethical Treatment: 10 Challenges / 2510.12844 / ISBN:https://doi.org/10.48550/arXiv.2510.12844 / Published by ArXiv / Version released on 2025-10-14 / on (web) Publishing site


Hiding in the AI Traffic: Abusing MCP for LLM-Powered Agentic Red Teaming / 2511.15998 / ISBN:https://doi.org/10.48550/arXiv.2511.15998 / Published by ArXiv / Version released on 2025-11-21 / on (web) Publishing site


The Making of Digital Ghosts: Designing Ethical AI Afterlives / 2511.20094 / ISBN:https://doi.org/10.48550/arXiv.2511.20094 / Published by ArXiv / Version released on 2025-11-25 / on (web) Publishing site


The Ethics of Generative AI / 2512.04598 / ISBN:https://doi.org/10.48550/arXiv.2512.04598 / Published by ArXiv / Version released on 2025-12-04 / on (web) Publishing site


PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI / 2512.24848 / ISBN:https://doi.org/10.48550/arXiv.2512.24848 / Published by ArXiv / Version released on 2025-12-31 / on (web) Publishing site


Guardrails for trust, safety, and ethical development and deployment of Large Language Models (LLM) / 2601.14298 / ISBN:https://doi.org/10.48550/arXiv.2601.14298 / Published by ArXiv / Version released on 2026-01-16 / on (web) Publishing site


Human Society-Inspired Approaches to Agentic AI Security: The 4C Framework / 2602.01942 / ISBN:https://doi.org/10.48550/arXiv.2602.01942 / Published by ArXiv / Version released on 2026-02-02 / on (web) Publishing site


Futuring Social Assemblages: How Enmeshing AIs into Social Life Challenges the Individual and the Interpersonal / 2602.03958 / ISBN:https://doi.org/10.48550/arXiv.2602.03958 / Published by ArXiv / Version released on 2026-02-03 / on (web) Publishing site


Reliable and Responsible Foundation Models: A Comprehensive Survey / 2602.08145 / ISBN:https://doi.org/10.48550/arXiv.2602.08145 / Published by ArXiv / Version released on 2026-02-04 / on (web) Publishing site