相关论文: Jailbreaking LLMs Without Gradients or Priors: Eff…

Recent advancements in Large Language Models (LLMs) have showcased remarkable capabilities across various tasks in different domains. However, the emergence of biases and the potential for generating harmful content in LLMs, particularly…

We introduce LLMStinger, a novel approach that leverages Large Language Models (LLMs) to automatically generate adversarial suffixes for jailbreak attacks. Unlike traditional methods, which require complex prompt engineering or white-box…

Jailbreak attacks in large language models (LLMs) entail inducing the models to generate content that breaches ethical and legal norm through the use of malicious prompts, posing a substantial threat to LLM security. Current strategies for…

Despite the remarkable performance of Large Language Models (LLMs), they remain vulnerable to jailbreak attacks, which can compromise their safety mechanisms. Existing studies often rely on brute-force optimization or manual design, failing…

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and…

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To…

Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

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…

Large Language Models (LLMs) have transformed task automation and content generation across various domains while incorporating safety filters to prevent misuse. We introduce a novel jailbreaking framework that employs distributed prompt…

Adversarial attacks against deep neural networks are continuously evolving. Without effective defenses, they can lead to catastrophic failure. The long-standing and arguably most powerful natural defense system is the mammalian immune…

Large Language Models (LLMs) are becoming a prominent generative AI tool, where the user enters a query and the LLM generates an answer. To reduce harm and misuse, efforts have been made to align these LLMs to human values using advanced…

Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain highly vulnerable to jailbreak attacks. Existing guardrail methods typically rely on internal features or textual responses to detect malicious…

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…

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak methods exist, many…

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…

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

Strategic classification~(SC) explores how individuals or entities modify their features strategically to achieve favorable classification outcomes. However, existing SC methods, which are largely based on linear models or shallow neural…