Fairness, bias, transparency, and ethical AI considerations
Newest first · 6 reviewed on this page
Search insteadAaron J. Li, Nicolas Sanchez, Hao Huang +8
Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well addressed by existing red-teaming efforts. We propose Green Shielding, a user-centric agenda for…
Kiarash Ahi, Vaibhav Agrawal, Saeed Valizadeh
As AI shifts from human-in-the-loop interfaces to autonomous multi-agent systems capable of real-time code execution and tool integration through protocols like the Model Context Protocol (MCP), traditional SAST, DAST, and legacy AI safety methods fail to detect modern…
Marco Antonio Corallo, Andrea Agiollo, Mauro Conti +1
Neuro-Symbolic (NeSy) AI has recently emerged as a novel paradigm to enable trustworthy AI, aiming at integrating sub-symbolic neural perception with grounded symbolic reasoning. The neuro-symbolic integration process that characterizes these models has been proven beneficial to…
Chong-Hui Tan, Qinxu Ding
The rapid adoption of large language models (LLMs) in financial services has generated a growing literature on “responsible AI” in domains such as investment analysis, credit assessment, risk management, compliance, and financial advisory systems. Unlike earlier AI systems, LLMs…
Sakshi Jain
For a decade, responsible AI at internet scale rested on a reassuring assumption: that risk lives primarily in a model, it is a unit you can isolate, and that privacy, fairness and safety is therefore something you certify at model level, before launch. At LinkedIn, where AI…
James H. Senanu
The rapid integration of artificial intelligence (AI) systems into security-critical domains has introduced new vulnerabilities, exposing these systems to a growing spectrum of adversarial threats. Adversarial machine learning (AML) has emerged as a key area of research aimed at…
Jieyao Pang
Deep neural networks achieve strong performance on perception tasks but remain vulnerable to adversarial examples—imperceptibly perturbed inputs that induce confident misclassification. This dissertation reviews the adversarial attack–defence landscape and reports CIFAR-10…
Boxin Wang, Weixin Chen, Hengzhi Pei +7
Comprehensive trustworthiness evaluation of GPT models across 8 dimensions including toxicity, bias, robustness, privacy, fairness, and machine ethics.
Lichao Sun, Yue Huang, Haoran Wang +2
Comprehensive study of LLM trustworthiness across truthfulness, safety, fairness, robustness, privacy, and machine ethics with benchmarks.
Sayash Kapoor, Rishi Bommasani, Kevin Klyman +2
Analyzes the societal impacts of open-weight foundation models, including security implications of open vs closed model access.
Anthropic
Framework defining AI Safety Levels (ASL) for evaluating and managing risks from increasingly capable AI systems.
Xianjun Yang, Xiao Wang, Qi Zhang +4
Shows that RLHF can introduce shadow alignment where models exhibit harmful behaviors not present in the base model.
Yuntao Bai, Saurav Kadavath, Sandipan Kundu +44
Introduces Constitutional AI (CAI), a method for training AI systems to be harmless using a set of principles (a constitution) and AI-generated feedback, reducing reliance on human red teamers.