相关论文: MemMorph: Tool Hijacking in LLM Agents via Memory …

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…

Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs become more vulnerable…

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG)…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…

With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…

Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish instructions from data content make them vulnerable to…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability, but they also create attack surfaces when untrusted external…

Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box…

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…

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…

Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

Large Language Models (LLMs) have become a key foundation for enabling personalized smart home experiences. While existing studies have explored how smart home assistants understand user queries to control devices in real time, their…

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool names, descriptions, and return messages. We show that this convenience creates a…