Related papers: Memory Injection Attacks on LLM Agents via Query-O…

Large Language Models (LLMs) currently struggle to sequentially add new memories and integrate new knowledge. These limitations contrast with the human ability to continuously learn from new experiences and acquire knowledge throughout…

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. The usage of tool-calling and Retrieval Augmented Generation (RAG) allows…

Retrieval-augmented generation (RAG) has become central to large language model (LLM) deployments, grounding responses in enterprise or proprietary data to reduce hallucinations. However, this design introduces a new privacy risk: model…

Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks like computer-use agents. Yet, the safety implications of these extended contexts remain unclear. To…

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 models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Jailbreak attacks aim to exploit large language models (LLMs) by inducing them to generate harmful content, thereby revealing their vulnerabilities. Understanding and addressing these attacks is crucial for advancing the field of LLM…

The rapid development of Large Language Models (LLMs) has brought impressive advancements across various tasks. However, despite these achievements, LLMs still pose inherent safety risks, especially in the context of jailbreak attacks. Most…

Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly…

Large language models (LLMs) have demonstrated significant utility in a wide range of applications; however, their deployment is plagued by security vulnerabilities, notably jailbreak attacks. These attacks manipulate LLMs to generate…

A conversation with a large language model (LLM) is a sequence of prompts and responses, with each response generated from the preceding conversation. AI agents build such conversations automatically: given an initial human prompt, a…

Ensuring the safe use of agentic systems requires a thorough understanding of the range of malicious behaviors these systems may exhibit when under attack. In this paper, we evaluate the robustness of LLM-based agentic systems against…

Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, motivating the need for realistic adversarial prompts that elicit such failures. We formulate hallucination elicitation as a…

Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and…

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

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.…

Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. However, existing benchmarks predominantly frame long-term memory evaluation as fact…

Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and…

Recent advances in large language models (LLMs) have substantially accelerated the development of embodied agents. LLM-based multi-agent systems mitigate the inefficiency of single agents in complex tasks. However, they still suffer from…