相关论文: Hijacking Agent Memory: Stealthy Trojan Attacks Th…

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…

Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Self-evolving LLM agents update their internal state across sessions, often by writing and reusing long-term memory. This design improves performance on long-horizon tasks but creates a security risk: untrusted external content observed…

Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access or explicit…

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Equipping Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks. Specifically, contaminated or biased memory accumulation can trigger abnormal agent…

Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn…

Large language models (LLMs) have transformed the development of embodied intelligence. By providing a few contextual demonstrations, developers can utilize the extensive internal knowledge of LLMs to effortlessly translate complex tasks…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral…

Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model Context Protocol (MCP) has emerged as a unifying framework for integrating external tools…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Human-agent dialogues often exhibit topic continuity-a stable thematic frame that evolves through temporally adjacent exchanges-yet most large language model (LLM) agent memory systems fail to preserve it. Existing designs follow a…

Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems that extract, retrieve, and apply information across long-running conversations. However,…

Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…

With the development of large language models (LLMs) like ChatGPT, both their vast applications and potential vulnerabilities have come to the forefront. While developers have integrated multiple safety mechanisms to mitigate their misuse,…

The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major threat is indirect prompt injection, where attackers embed…

Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, information retrieval, and content discovery. Due to the…

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…