Related papers: MURMUR: Using cross-user chatter to break collabor…

To prevent the misuse of Large Language Models (LLMs) for malicious purposes, numerous efforts have been made to develop the safety alignment mechanisms of LLMs. However, as multiple LLMs become readily accessible through various…

While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also…

Agentic systems based on large language models (LLMs) operate not merely as text generators but as autonomous entities that dynamically retrieve information and invoke tools. This execution model shifts the attack surface from traditional…

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability: routine user-agent interactions can gradually reshape an…

Deep-research agents, i.e., systems that rely on multi-agent pipelines to iteratively retrieve, synthesize, and cite Web content in order to produce structured reports, are rapidly replacing traditional search for both routine and complex…

Advances in AI offer the prospect of manipulating beliefs and behaviors on a population-wide level. Large language models and autonomous agents now let influence campaigns reach unprecedented scale and precision. Generative tools can expand…

Trending topics have become a significant part of modern social media, attracting users to participate in discussions of breaking events. However, they also bring in a new channel for poisoning attacks, resulting in negative impacts on…

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions,…

Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant knowledge sources. It is particularly useful in chatbot…

While Large Language Model (LLM) multi-agent systems (MAS) offer a transformative approach to simulating human behavior in complex systems, it remains largely unexplored whether these simulations can replicate realistic structural and…

The rise of social media has been accompanied by a dark side with the ease of creating fake accounts and disseminating misinformation through coordinated attacks. Existing methods to identify such attacks often rely on thematic similarities…

Large language models (LLMs) are rapidly evolving into autonomous agents that cooperate across organizational boundaries, enabling joint disaster response, supply-chain optimization, and other tasks that demand decentralized expertise…

The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly…

Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g., graphs or tables), these methods typically suffer from low…

Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. Their potential to facilitate human coordination with many agents is a promising but largely under-explored area. Such capabilities would be helpful…

Mobile agents powered by vision-language models (VLMs) are increasingly adopted for tasks such as UI automation and camera-based assistance. These agents are typically fine-tuned using small-scale, user-collected data, making them…

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

Large language models (LLMs) have significantly enhanced the performance of numerous applications, from intelligent conversations to text generation. However, their inherent security vulnerabilities have become an increasingly significant…