Related papers: Thought Virus: Viral Misalignment via Subliminal P…

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

Sequential multi-agent large language model (LLM) systems are increasingly deployed in sensitive domains such as healthcare, finance, and enterprise decision-making, where multiple specialized agents collaboratively process a single user…

This paper concerns sequential hypothesis testing in competitive multi-agent systems where agents exchange potentially manipulated information. Specifically, a two-agent scenario is studied where each agent aims to correctly infer the true…

As large language models (LLMs) are increasingly deployed in healthcare, ensuring their safety, particularly within collaborative multi-agent configurations, is paramount. In this paper we introduce MedSentry, a benchmark comprising 5 000…

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Research shows that the way strategic scenarios are framed linguistically can affect…

We identify and formalize a novel security risk: Context-Fragmented Violations (CFVs) - a class of policy breaches where individual agent actions appear locally safe and reasonable, yet collectively violate organizational policies because…

Modern information environments, especially social media, are highly complex systems that exceed individual processing capacities such as humans' limited attention. This environment/cognition mismatch can increase susceptibility to…

Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Contrary to expectations, our investigations reveal that the…

As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable performance and robust…

Recent advances in prompting techniques and multi-agent systems for Large Language Models (LLMs) have produced increasingly complex approaches. However, we lack a framework for characterizing and comparing prompting techniques or…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…

Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning, positioning them as promising tools for supporting human problem-solving. However, what happens when their performance is affected by misinformation, i.e.,…

We describe a vulnerability in language models (LMs) trained with user feedback, whereby a single user can persistently alter LM knowledge and behavior given only the ability to provide prompts and upvote / downvote feedback on LM outputs.…

Beyond simple text generation, Large Language Models (LLMs) have evolved into agentic systems capable of planning and interacting with external tools to solve complex tasks. This evolution involves fine-tuning LLMs on agent-specific tasks…

Multi-agent Large Language Model (LLM) systems have emerged as powerful architectures for complex task decomposition and collaborative problem-solving. However, their long-term behavioral stability remains largely unexamined. This study…

Safety risks arise as large language model-based agents solve complex tasks with tools, multi-step plans, and inter-agent messages. However, deployer-written policies in natural language are ambiguous and context dependent, so they map…

Consensus problem of high-order integral multi-agent systems under switching directed topology is considered in this study. Depending on whether the agent's full state is available or not, two distributed protocols are proposed to ensure…

Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can induce various forms of misalignment without explicit…

Large Language Models (LLMs), though shown to be effective in many applications, can vary significantly in their response quality. In this paper, we investigate this problem of prompt fairness: specifically, the phrasing of a prompt by…