Related papers: A Framework for Formalizing LLM Agent Security
Recent advances in the intrinsic reasoning capabilities of large language models (LLMs) have given rise to LLM-based agent systems that exhibit near-human performance on a variety of automated tasks. However, although these systems share…
As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…
Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an…
In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…
From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research…
Agent hijacking, highlighted by OWASP as a critical threat to the Large Language Model (LLM) ecosystem, enables adversaries to manipulate execution by injecting malicious instructions into retrieved content. Most existing attacks rely on…
With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly…
Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…
The widespread adoption of open-source software (OSS) has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…
Game theory has long served as a foundational tool in cybersecurity to test, predict, and design strategic interactions between attackers and defenders. The recent advent of Large Language Models (LLMs) offers new tools and challenges for…
Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such…
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,…
Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…
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…
Language agents powered by large language models (LLMs) have seen exploding development. Their capability of using language as a vehicle for thought and communication lends an incredible level of flexibility and versatility. People have…
This paper presents a secure-by-construction planning and control framework for multi-agent systems subject to linear temporal logic (LTL) specifications. The framework protects sensitive information from a passive intruder with partial…
Current LLM-based frameworks for text anonymization usually rely on remote API services from powerful LLMs, which creates an inherent privacy paradox: users must disclose the raw data to untrusted third parties for guaranteed privacy…
LLMs have made impressive progress, but their growing capabilities also expose them to highly flexible jailbreaking attacks designed to bypass safety alignment. While many existing defenses focus on known types of attacks, it is more…
As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using…