相关论文: A Representation Engineering Perspective on the Ef…

As the integration of the Large Language Models (LLMs) into various applications increases, so does their susceptibility to misuse, raising significant security concerns. Numerous jailbreak attacks have been proposed to assess the security…

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not involve a specific…

We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it…

Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak…

Large language models (LLMs) remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints gradually. These attacks target different harm categories through distinct conversational…

Multi-turn interactions with language models (LMs) pose critical safety risks, as harmful intent can be strategically spread across exchanges. Yet, the vast majority of prior work has focused on single-turn safety, while adaptability and…

LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work mitigates this issue…

As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known as jailbreaks. The…

The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. However, recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations, often with…

Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…

Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be deemed harmful.Efforts to mitigate this risk include…

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) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberately mislead them into…

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…

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…

By incorporating visual inputs, Multimodal Large Language Models (MLLMs) extend LLMs to support visual reasoning. However, this integration also introduces new vulnerabilities, making MLLMs susceptible to multimodal jailbreak attacks and…

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely…

Large Reasoning Models (LRMs) have recently demonstrated impressive performances across diverse domains. However, how the safety of Large Language Models (LLMs) benefits from enhanced reasoning capabilities against jailbreak queries remains…