Related papers: Benchmarking and Understanding Safety Risks in AI …
AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation…
Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…
Understanding public perception of artificial intelligence (AI) and the tradeoffs between potential risks and benefits is crucial, as these perceptions might shape policy decisions, influence innovation trajectories for successful market…
Autonomous AI agents can now programmatically hire human workers through marketplaces using REST APIs and Model Context Protocol (MCP) integrations. This creates an attack surface analogous to CAPTCHA-solving services but with…
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…
Evaluating the safety of AI Systems is a pressing concern for organizations deploying them. In addition to the societal damage done by the lack of fairness of those systems, deployers are concerned about the legal repercussions and the…
As Conversational Artificial Intelligence (AI) becomes more integrated into everyday life, AI-powered chatbot mobile applications are increasingly adopted across industries, particularly in the healthcare domain. These chatbots offer…
Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy…
Recent advances in AI has made automated analysis of complex media content at scale possible while generating actionable insights regarding character representation along such dimensions as gender and age. Past works focused on quantifying…
Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…
The rapid growth of artificial intelligence (AI) technologies has raised major privacy and ethical concerns. However, existing AI incident taxonomies and guidelines lack grounding in real-world cases, limiting their effectiveness for…
Large Language Models (LLMs) are increasingly used by teenagers and young adults in everyday life, ranging from emotional support and creative expression to educational assistance. However, their unique vulnerabilities and risk profiles…
Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to…
International cooperation is common in AI research, including between geopolitical rivals. While many experts advocate for greater international cooperation on AI safety to address shared global risks, some view cooperation on AI with…
Over a billion users globally interact with AI systems engineered to mimic human traits. This development raises concerns that anthropomorphism, the attribution of human characteristics to AI, may foster over-reliance and misplaced trust.…
As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the…
While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…
In recent years, AI has demonstrated remarkable capabilities in simulating human behaviors, particularly those implemented with large language models (LLMs). However, due to the lack of systematic evaluation of LLMs' simulated behaviors,…
As Large Language Models (LLMs) are increasingly deployed in safety-critical applications, robust content moderation becomes essential. We present a comprehensive evaluation of 14 open-source safety guard models on a curated benchmark of…
As AI systems become more capable, widely deployed, and increasingly autonomous in critical areas such as cybersecurity, biological research, and healthcare, ensuring their safety and alignment with human values is paramount. Machine…