Related papers: AgentSentinel: An End-to-End and Real-Time Securit…

This paper proposes a novel architectural framework aimed at enhancing security and reliability in multi-agent systems (MAS). A central component of this framework is a network of Sentinel Agents, functioning as a distributed security layer…

The acquisition of agentic capabilities has transformed LLMs from "knowledge providers" to "action executors", a trend that while expanding LLMs' capability boundaries, significantly increases their susceptibility to malicious use. Previous…

Driven by the rapid development of Large Language Models (LLMs), LLM-based agents have been developed to handle various real-world applications, including finance, healthcare, and shopping, etc. It is crucial to ensure the reliability and…

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…

Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces…

Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in…

Prompt injection attacks represent a major vulnerability in Large Language Model (LLM) deployments, where malicious instructions embedded in user inputs can override system prompts and induce unintended behaviors. This paper presents a…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

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…

Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…

Designing realistic and adaptive networked threat scenarios remains a core challenge in cybersecurity research and training, still requiring substantial manual effort. While large language models (LLMs) show promise for automated synthesis,…

Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our…

Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…

In the current rapidly changing digital environment, businesses are under constant stress to ensure that their systems are secured. Security audits help to maintain a strong security posture by ensuring that policies are in place, controls…

Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege…

LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. However, recent studies have shown that these agents face severe security risks, which…

Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades…

In today's digital world, casual user-generated content often contains subtle cues that may inadvertently expose sensitive personal attributes. Such risks underscore the growing importance of effective text anonymization to safeguard…