Related papers: PUZZLED: Jailbreaking LLMs through Word-Based Puzz…
Most traditional AI safety research has approached AI models as machines and centered on algorithm-focused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can…
Exploring the capabilities of Large Language Models (LLMs) in puzzle solving unveils critical insights into their potential and challenges in AI, marking a significant step towards understanding their applicability in complex reasoning…
Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful content, a risk that has been further amplified by various jailbreak attacks. Existing jailbreak…
Large language models (LLMs) have become increasingly integrated with various applications. To ensure that LLMs do not generate unsafe responses, they are aligned with safeguards that specify what content is restricted. However, such…
Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…
Jailbreak attacks on Language Model Models (LLMs) entail crafting prompts aimed at exploiting the models to generate malicious content. Existing jailbreak attacks can successfully deceive the LLMs, however they cannot deceive the human.…
Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn attacks, lack coverage across languages, and rely on limited taxonomies that either fail to…
Large language models (LLMs) have been increasingly applied to various domains, which triggers increasing concerns about LLMs' safety on specialized domains, e.g. medicine. Despite prior explorations on general jailbreaking attacks, there…
Large Language Models (LLMs) are widely used in natural language processing but face the risk of jailbreak attacks that maliciously induce them to generate harmful content. Existing jailbreak attacks, including character-level and…
Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…
This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses. The learning-style queries are constructed by a novel…
Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…
Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…
Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective. However, previous…
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…
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…
Large language models (LLMs) have gained widespread recognition for their superior comprehension and have been deployed across numerous domains. Building on Chain-of-Thought (CoT) ideology, Large Reasoning models (LRMs) further exhibit…
Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these mechanisms remain poorly understood. Existing studies predominantly analyze jailbreak prompts by…
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…
We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generate harmful outputs. By simply instructing the LLM to deviate…