Related papers: LLMs Encode Harmfulness and Refusal Separately

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer questions that are unethical or harmful, raising concerns about…

Large language models (LLMs) are increasingly deployed in medical contexts, raising critical concerns about safety, alignment, and susceptibility to adversarial manipulation. While prior benchmarks assess model refusal capabilities for…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

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…

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility.…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction,…