相关论文: Toward Securing AI Agents Like Operating Systems

Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…

While new technologies emerge, human errors always looming. Software supply chain is increasingly complex and intertwined, the security of a service has become paramount to ensuring the integrity of products, safeguarding data privacy, and…

As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trustworthy deployment in…

Agentic systems built on large language models (LLMs) are increasingly being used for complex security tasks, including binary reverse engineering (RE). Despite recent growth in popularity and capability, these systems continue to face…

The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific…

AI-based systems, including Large Language Models (LLM), impact millions by supporting diverse tasks but face issues like misinformation, bias, and misuse. AI ethics is crucial as new technologies and concerns emerge, but objective,…

Autonomous agents have long been a prominent research focus in both academic and industry communities. Previous research in this field often focuses on training agents with limited knowledge within isolated environments, which diverges…

Attacks powered by Large Language Model (LLM) agents represent a growing threat to modern cybersecurity. To address this concern, we present LLM Honeypot, a system designed to monitor autonomous AI hacking agents. By augmenting a standard…

Multi-agent systems leverage advanced AI models as autonomous agents that interact, cooperate, or compete to complete complex tasks across applications such as robotics and traffic management. Despite their growing importance, safety in…

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We…

With the continuous evolution of Large Language Models (LLMs), LLM-based agents have advanced beyond passive chatbots to become autonomous cyber entities capable of performing complex tasks, including web browsing, malicious code and…

The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret…

As the strength of Large Language Models (LLMs) has grown over recent years, so too has interest in their use as the underlying models for autonomous agents. Although LLMs demonstrate emergent abilities and broad expertise across natural…

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,…

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

Large language models (LLMs) have evolved AI assistants into autonomous reasoning engines that maintain context, invoke tools, and pursue long-horizon tasks. This has spurred Agent Operating Systems (Agent OS) as kernel-like layers for…

We argue that LLM agent security is fundamentally an agent-human interaction (AHI) problem, not a purely algorithmic one. To substantiate this position, we conduct a systematic analysis of 59 academic papers, 21 production agent systems,…

Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, planning, and goal-directed action. While LLM agents are…

The integration of Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) into mobile GUI agents has significantly enhanced user efficiency and experience. However, this advancement also introduces potential security…

Large language models (LLMs) and their agentic frameworks are increasingly adopted to perform development tasks such as automated program repair (APR). While prior work has identified security risks in LLM-generated code, most have focused…