相关论文: AutoAdv: Automated Adversarial Prompting for Multi…

Large Language Models (LLMs) continue to exhibit vulnerabilities to jailbreaking attacks: carefully crafted malicious inputs intended to circumvent safety guardrails and elicit harmful responses. As such, we present AutoAdv, a novel…

GPT-4V has attracted considerable attention due to its extraordinary capacity for integrating and processing multimodal information. At the same time, its ability of face recognition raises new safety concerns of privacy leakage. Despite…

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…

Multi-turn jailbreak attacks have proven effective against text-only large language models (LLMs), where malicious content is gradually introduced to bypass safety alignment. However, effectively extending such attacks to large…

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that…

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

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…

Recent large language model (LLM) defenses have greatly improved models' ability to refuse harmful queries, even when adversarially attacked. However, LLM defenses are primarily evaluated against automated adversarial attacks in a single…

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…

Recent advances in large language models (LLMs) have raised concerns about jailbreaking attacks, i.e., prompts that bypass safety mechanisms. This paper investigates the use of multi-agent LLM systems as a defence against such attacks. We…

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

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…

Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become pronounced in multi-turn multi-modal scenarios, where harmful intent can be gradually…

Safety fine-tuning of language models typically requires a curated adversarial dataset. We take a different approach: score each candidate prompt's difficulty by how often the target model's own rollouts are judged harmful, then fine-tune…

While defenses against single-turn jailbreak attacks on Large Language Models (LLMs) have improved significantly, multi-turn jailbreaks remain a persistent vulnerability, often achieving success rates exceeding 70% against models optimized…

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,…

In the rapidly evolving field of machine learning, adversarial attacks present a significant challenge to model robustness and security. Decision-based attacks, which only require feedback on the decision of a model rather than detailed…

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,…

In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing…

We introduce Tempest, a multi-turn adversarial framework that models the gradual erosion of Large Language Model (LLM) safety through a tree search perspective. Unlike single-turn jailbreaks that rely on one meticulously engineered prompt,…