Related papers: TrinityGuard: A Unified Framework for Safeguarding…

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed…

Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information…

Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive performance in many areas. However, MAS are typically distributed across different devices…

As LLMs become widespread across diverse applications, concerns about the security and safety of LLM interactions have intensified. Numerous guardrail models and benchmarks have been developed to ensure LLM content safety. However, existing…

While large language model-based agents demonstrate great potential in collaborative tasks, their interactivity also introduces security vulnerabilities. In this paper, we propose and model group collusive attacks, a highly destructive…

As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores often jointly reflect model capability and the implementation choices each benchmark is…

Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems", where their ability to "interact in multi-turn,…

LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of attacks, such as tool poisoning and malicious instructions, that compromise their execution…

The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…

The digital world is witnessing the rapid rise of LLM-based multi-agent systems (MASs) and their powerful applications. However, their security remains insufficiently understood, as existing evaluations are largely limited to narrow attack…

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…

LLM agents are increasingly deployed in long-horizon, complex environments to solve challenging problems, but this expansion exposes them to long-horizon attacks that exploit multi-turn user-agent-environment interactions to achieve…

Large Language Model (LLM) agents increasingly operate across domains such as robotics, virtual assistants, and web automation. However, their stochastic decision-making introduces safety risks that are difficult to anticipate during…

With the proliferation of LLM-driven multi-agent systems (MAS), the security of Web links has become a critical concern. Once MAS is induced to trust a malicious link, attackers can use it as a springboard to expand the attack surface. In…

Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety frameworks and guardrails, current protective measures exhibit…

Recent advancements in autonomous multi-agent systems (MAS) based on large language models (LLMs) have enhanced the application scenarios and improved the capability of LLMs to handle complex tasks. Despite demonstrating effectiveness,…

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning…

The rapid advancement of large language models (LLMs) has empowered intelligent agents to leverage diverse external tools for solving complex real-world problems. However, this reliance introduces new challenges, as extended contexts and…