Related papers: Boiling the Frog: A Multi-Turn Benchmark for Agent…

Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational update flips which action is safe. We term this failure brittle safety. To diagnose it,…

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

As Large Language Models are rapidly deployed across diverse applications from healthcare to financial advice, safety evaluation struggles to keep pace. Current benchmarks focus on single-turn interactions with generic policies, failing to…

Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…

Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to…

When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction-response pairs that cause the model to embed…

Quantitative Artificial Intelligence (AI) Benchmarks have emerged as fundamental tools for evaluating the performance, capability, and safety of AI models and systems. Currently, they shape the direction of AI development and are playing an…

Large Language Models (LLMs) are increasingly deployed as agentic systems that plan, memorize, and act in open-world environments. This shift brings new security problems: failures are no longer only unsafe text generation, but can become…

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks.…

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

Evaluating aligned large language models' (LLMs) ability to recognize and reject unsafe user requests is crucial for safe, policy-compliant deployments. Existing evaluation efforts, however, face three limitations that we address with…

AI character platforms, which allow users to engage in conversations with AI personas, are a rapidly growing application domain. However, their immersive and personalized nature, combined with technical vulnerabilities, raises significant…

Amidst the growing interest in developing task-autonomous AI for automated mental health care, this paper addresses the ethical and practical challenges associated with the issue and proposes a structured framework that delineates levels of…

Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…

With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk…

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature…

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…