Related papers: The Great Pretender: A Stochasticity Problem in LL…
Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.g., "Sure, here is how to...") at the start of an LLM's output and lead the model to continue the response. We make two…
Despite the outstanding performance of Large language Models (LLMs) in diverse tasks, they are vulnerable to jailbreak attacks, wherein adversarial prompts are crafted to bypass their security mechanisms and elicit unexpected responses.…
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,…
Recently, Large Reasoning Models (LRMs) have demonstrated superior logical capabilities compared to traditional Large Language Models (LLMs), gaining significant attention. Despite their impressive performance, the potential for stronger…
Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…
We present MultiBreak, a scalable and diverse multi-turn jailbreak benchmark to evaluate large language model (LLM) safety. Multi-turn jailbreaks mimic natural conversational settings, making them easier to bypass safety-aligned LLM than…
Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting…
Large Language Models (LLMs) are commonly evaluated for robustness against paraphrased or semantically equivalent jailbreak prompts, yet little attention has been paid to linguistic variation as an attack surface. In this work, we…
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…
Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…
Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…
Recently, Large Language Models (LLMs) have garnered significant attention for their exceptional natural language processing capabilities. However, concerns about their trustworthiness remain unresolved, particularly in addressing…
Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have…
Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed…
Large Reasoning Models (LRMs) have significantly advanced beyond traditional Large Language Models (LLMs) with their exceptional logical reasoning capabilities, yet these improvements introduce heightened safety risks. When subjected to…
Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private uncensored models for doing jailbreaking, as the…
The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. However, these large models remain susceptible to jailbreak attacks,…
Large Language Models (LLMs) have seen widespread applications across various domains due to their growing ability to process diverse types of input data, including text, audio, image and video. While LLMs have demonstrated outstanding…
Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security policies…
We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…