Related papers: Stop Fixating on Prompts: Reasoning Hijacking and …

Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of…

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts.…

As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect security vulnerabilities in LLMs without manual labor.…

Large Language Models (LLMs), especially their compact efficiency-oriented variants, remain susceptible to jailbreak attacks that can elicit harmful outputs despite extensive alignment efforts. Existing adversarial prompt generation…

Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective (e.g., from "summarizing emails" to "phishing users"). In this paper, we argue that this…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious…

This paper proposes a game theoretic framework that models the interaction between prompt engineers and large language models (LLMs) as a two player extensive form game coupled with a Rapidly exploring Random Trees (RRT) search over prompt…

As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning…

Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values. However, even meticulously aligned LLMs remain vulnerable to malicious manipulations such as…

Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance…

Large Language Models (LLMs) are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment…

LLM-based agents execute real-world workflows via tools and memory. These affordances enable ill-intended adversaries to also use these agents to carry out complex misuse scenarios. Existing agent misuse benchmarks largely test…

The systems and software powered by Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vulnerable to prompt-based attacks, with jailbreaking attacks…

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…

Modern large language model (LLM) developers typically conduct a safety alignment to prevent an LLM from generating unethical or harmful content. Recent studies have discovered that the safety alignment of LLMs can be bypassed by…

Large Language Models (LLMs) trained with reinforcement learning and verifiable rewards have achieved strong results on complex reasoning tasks. Recent work extends this paradigm to a multi-agent setting, where a meta-thinking agent…

Large language models (LLMs) are increasingly used as autonomous agents, tackling tasks from robotics to web navigation. Their performance depends on the underlying base agent. Existing methods, however, struggle with long-context reasoning…

User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and proactively engages in negotiation by challenging or bargaining. However, current methods…

For safety reasons, large language models (LLMs) are trained to refuse harmful user instructions, such as assisting dangerous activities. We study an open question in this work: does the desired safety refusal, typically enforced in chat…