相关论文: ILION: Deterministic Pre-Execution Safety Gates fo…
Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual…
AI agents are entering high-risk production settings, where they use tools, retain context, follow policies, handle private data, and interact with users over multiple turns. Yet many evaluation methods still judge isolated outputs or…
Large language models (LLMs) deployed as agents introduce significant safety risks in clinical settings due to their potential for error and single points of failure. We introduce Tiered Agentic Oversight (TAO), a hierarchical multi-agent…
Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct…
As large language models (LLMs) improve, so do their offensive applications: frontier agents now generate working exploits for under $50 in compute (Heelan, 2026). Defensive incident response (IR) agents must keep pace, but existing…
Post-mortem analysis of compromised systems is a key aspect of cyber forensics, today a mostly manual, slow, and error-prone task. Agentic AI, i.e., LLM-powered agents, is a promising avenue for automation. However, applying such agents to…
This paper critically evaluates the "Law-Following AI" (LFAI) framework proposed by O'Keefe et al. (2025), which seeks to embed legal compliance as a superordinate design objective for advanced AI agents and enable them to bear legal duties…
The rapid expansion of low-altitude economy Internet of Things (LAE-IoT) networks has created unprecedented security challenges due to dynamic three-dimensional mobility patterns, distributed autonomous operations, and severe resource…
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…
AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can…
An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from its audit record -- F1 gate-bypass, F2 audit-forgery, silent host failure, F4 wrong-target,…
Agentic AI systems, possessing capabilities for autonomous planning and action, show great potential across diverse domains. However, their practical deployment is hindered by challenges in aligning their behavior with varied human values,…
This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when…
Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…
Modern software infrastructure increasingly relies on LLM agents for development and maintenance, such as Claude Code and Gemini-cli. However, these AI agents differ fundamentally from traditional deterministic software, posing a…
For flexible yet safe imitation learning (IL), we propose theory and a modular method, with a safety layer that enables a closed-form probability density/gradient of the safe generative continuous policy, end-to-end generative adversarial…
The widespread adoption of Large Language Models (LLMs) has revolutionized AI deployment, enabling autonomous and semi-autonomous applications across industries through intuitive language interfaces and continuous improvements in model…
Agentic AI systems are emerging as powerful tools for automating complex, multi-step tasks across various industries. One such industry is telecommunications, where the growing complexity of next-generation radio access networks (RANs)…
Real-time guardrails require evaluation that is accurate, cheap, and fast - yet today's default, LLM-as-a-judge (LLMAJ), is slow, expensive, and operationally non-deterministic due to multi-token generation. We present Luna-2, a novel…
As researchers continue to optimize AI agents for more effective task execution within operating systems, they often overlook a critical security concern: the ability of these agents to detect "impostors" within their environment. Through…