Related papers: Agent-Sentry: Bounding LLM Agents via Execution Pr…
As LLM-based agents increasingly operate in high-stakes domains with real-world consequences, ensuring their behavioral safety becomes paramount. The dominant oversight paradigm, LLM-as-a-Judge, faces a fundamental dilemma: how can…
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…
Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency…
Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome…
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…
We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model (LLM)-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…
Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…
Agentic systems involved in high-stake decision-making under adversarial pressure need formal guarantees not offered by existing approaches. Motivated by the operational needs of security operations centers (SOCs) that must configure…
Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…
Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…
Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…
The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…
Modern LLM based agents are no longer passive text generators. They read repositories, call tools, browse the web, execute code, maintain memory, communicate with other agents, and act through long horizon workflows. This shift moves the…
Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…
Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and…
Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…
Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such…