相关论文: AgentShield: Deception-based Compromise Detection …

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…

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on…

The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs…

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK…

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…

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models (LLMs), Vision-Language Models (VLMs), and new agentic AI systems, like LangChain and…

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…

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…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Multimodal agents built on large vision-language models (LVLMs) are increasingly deployed in open-world settings but remain highly vulnerable to prompt injection, especially through visual inputs. We introduce AgentTypo, a black-box…

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…

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based…

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 model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against…

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300…

Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish user-specified tasks. However, they are highly…

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…