相关论文: Mapping the Exploitation Surface: A 10,000-Trial T…

With the proliferation of LLM-integrated applications such as GPT-s, millions are deployed, offering valuable services through proprietary instruction prompts. These systems, however, are prone to prompt extraction attacks through…

Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and exploit acquired…

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

This study reveals how frontier Large Language Models LLMs can "game the system" when faced with impossible situations, a critical security and alignment concern. Using a novel textual simulation approach, we presented three leading LLMs…

Large Language Models (LLMs) are increasingly used for automated software development, making their ability to preserve secure coding practices critical. In practice, however, many security requirements are implicit or underspecified,…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…

Reinforcement learning (RL) trained language model agents with tool access are increasingly deployed in coding assistants, research tools, and autonomous systems. We introduce the Reward Hacking Benchmark (RHB), a suite of multi-step tasks…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…

Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of LLMs in chat mode, the security…

As large language models (LLMs) permeate more and more applications, an assessment of their associated security risks becomes increasingly necessary. The potential for exploitation by malicious actors, ranging from disinformation to data…

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…

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents -- which use external…

While the widespread deployment of Large Language Models (LLMs) holds great potential for society, their vulnerabilities to adversarial manipulation and exploitation can pose serious safety, security, and ethical risks. As new threats…

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…