Related papers: Jailbreaking Frontier Foundation Models Through In…

Extensive work has been devoted to improving the safety mechanism of Large Language Models (LLMs). However, LLMs still tend to generate harmful responses when faced with malicious instructions, a phenomenon referred to as "Jailbreak…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more…

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…

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their original settings, but their attacks vary substantially in…

The rapid proliferation of Large Language Models (LLMs) has heightened concerns regarding their exposure to jailbreak attacks, which craft adversarial inputs designed to elicit unsafe content. Although proprietary models such as GPT-4 have…

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Large language models (LLMs) are designed to align with human values in their responses. This study exploits LLMs with an iterative prompting technique where each prompt is systematically modified and refined across multiple iterations to…

Many-shot jailbreaking (MSJ) is an adversarial technique that exploits the long context windows of modern LLMs to circumvent model safety training by including in the prompt many examples of a "fake" assistant responding inappropriately…

Hidden malicious intent in multi-turn dialogue poses a growing threat to deployed large language models (LLMs). Rather than exposing a harmful objective in a single prompt, increasingly capable attackers can distribute their intent across…

With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment. Current benchmarks primarily concentrate on single-turn dialogues or a single jailbreak attack method…

Aligned large language models (LLMs) remain vulnerable to jailbreak attacks. Recent mechanistic studies have identified latent features and representation shifts associated with jailbreak success, but they leave a more fundamental question…

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…

Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understand context and recognize user intent. This creates exploitable vulnerabilities…

Current LLM safety alignment techniques improve model robustness against adversarial attacks, but overlook whether and how LLMs can recover helpfulness when benign users clarify their intent. We introduce CarryOnBench, the first interactive…