相关论文: Topology Matters: Measuring Memory Leakage in Mult…

Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting expressiveness, they also expose new vulnerabilities in graph learning through text-based…

Object-Goal Navigation (ObjectNav) requires an agent to find and navigate to a target object category in unknown environments. While recent Large Language Model (LLM)-based agents exhibit zero-shot reasoning, they often rely on a "reactive"…

With the widespread application of artificial intelligence technologies in face recognition and other fields, data privacy security issues have received extensive attention, especially the \textit{right to be forgotten} emphasized by…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, code generation, and complex planning. Simultaneously, Multi-Agent Systems (MAS) have garnered attention for their potential to enable…

This work evaluates the performance of Cyber Threat Intelligence (CTI) extraction methods in identifying attack techniques from threat reports available on the web using the MITRE ATT&CK framework. We analyse four configurations utilising…

Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (GNNs). While this integration leverages rich relational…

LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of…

Memory leaks are prevalent in various real-world software projects, thereby leading to serious attacks like denial-of-service. Though prior methods for detecting memory leaks made significant advance, they often suffer from low accuracy and…

Memory is essential for enabling large language models to support long-horizon reasoning, yet existing memory systems remain unreliable and difficult to debug. Tracing memory's dynamic evolution is crucial to understand how information is…

Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…

Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relationships with rich textual semantics for diverse applications. However, the effectiveness of…

Multi-Agent Systems (MAS) offer a powerful paradigm for solving complex problems, yet their performance is critically dependent on the design of their underlying collaboration topology. As MAS become increasingly deployed in web services…

Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…

Animals are able to discover the topological map (graph) of surrounding environment, which will be used for navigation. Inspired by this biological phenomenon, researchers have recently proposed to generate graph representation for Markov…

LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…

Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically…

In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage. This paper investigates a black-box privacy attack, i.e.,…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

Large Language Models are being increasingly deployed as the decision-making core of autonomous agents capable of effecting change in external environments. Yet, in conversational benchmarks, which simulate real-world customer-centric issue…

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…