Related papers: Depth Charge: Jailbreak Large Language Models from…
Large foundation models (LFMs) are susceptible to two distinct vulnerabilities: hallucinations and jailbreak attacks. While typically studied in isolation, we observe that defenses targeting one often affect the other, hinting at a deeper…
Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…
Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize across both language and vision tasks, LLMs and MLLMs have shown vulnerability to jailbreaking, generating textual outputs that…
As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety.…
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…
Large Language Models (LLMs) have achieved remarkable success in various domains but remain vulnerable to adversarial jailbreak attacks. Existing prompt-defense strategies, including parameter-modifying and parameter-free approaches, face…
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…
Large Audio Language Models (LALMs) have made significant progress. While increasingly deployed in real-world applications, LALMs face growing safety risks from jailbreak attacks that bypass safety alignment. However, there remains a lack…
Although Aligned Large Language Models (LLMs) are trained to refuse harmful requests, they remain vulnerable to jailbreak attacks. Unfortunately, existing methods often focus on surface-level patterns, overlooking the deeper attack…
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 seen widespread applications across various domains, yet remain vulnerable to adversarial prompt injections. While most existing research on jailbreak attacks and hallucination phenomena has focused…
With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…
The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…
Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…
The rapid adoption of large language models (LLMs) has brought both transformative applications and new security risks, including jailbreak attacks that bypass alignment safeguards to elicit harmful outputs. Existing automated jailbreak…
Despite extensive safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. However, existing methods generally lack the capability for continuous learning and self-evolution from interactions, limiting the…
Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…
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…
As large language models (LLMs) are increasingly deployed in diverse applications, including chatbot assistants and code generation, aligning their behavior with safety and ethical standards has become paramount. However, jailbreak attacks,…
Security vulnerabilities are increasingly prevalent in modern software and they are widely consequential to our society. Various approaches to defending against these vulnerabilities have been proposed, among which those leveraging deep…