相关论文: Red-Teaming Agent Execution Contexts: Open-World S…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution…

Personalized computer-use agents are rapidly moving from expert communities into mainstream use. Unlike conventional chatbots, these systems can install skills, invoke tools, access private resources, and modify local environments on users'…

Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…

Agentic AI systems automate enterprise workflows but existing defenses--guardrails, semantic filters--are probabilistic and routinely bypassed. We introduce authenticated workflows, the first complete trust layer for enterprise agentic AI.…

The rapid deployment of Large language model (LLM) agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standardized evaluation benchmarks for these agents in dynamic…

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or…

Adversarial examples can be useful for identifying vulnerabilities in AI systems before they are deployed. In reinforcement learning (RL), adversarial policies can be developed by training an adversarial agent to minimize a target agent's…

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent…

Language agents have shown impressive problem-solving skills within defined settings and brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a pressing need for agents that can flexibly adapt to…

OpenClaw-like agents offer substantial productivity benefits, yet they are insecure by default because they combine untrusted inputs, autonomous action, extensibility, and privileged system access within a single execution loop. We use…

We propose an extension to the OWASP Multi-Agentic System (MAS) Threat Modeling Guide, translating recent anticipatory research in multi-agent security (MASEC) into practical guidance for addressing challenges unique to large language model…

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…