Related papers: Not All Tokens Are Created Equal: Query-Efficient …

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

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…

With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical concern. Despite significant efforts in safety alignment, current LLMs remain vulnerable to jailbreaking attacks. However, the root causes…

Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…

Fuzzing is highly effective in detecting bugs due to the key contribution of randomness. However, randomness significantly reduces the efficiency of fuzzing, causing it to cost days or weeks to expose bugs. Even though directed fuzzing…

Deep learning (DL) libraries, widely used in AI applications, often contain vulnerabilities like buffer overflows and use-after-free errors. Traditional fuzzing struggles with the complexity and API diversity of DL libraries such as…

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Software fuzzing has become a cornerstone in automated vulnerability discovery, yet existing mutation strategies often lack semantic awareness, leading to redundant test cases and slow exploration of deep program states. In this work, I…

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

Multi-robot swarms play an essential role in complex missions including battlefield reconnaissance, agricultural pest monitoring, as well as disaster search and rescue. Unfortunately, given the complexity of swarm algorithms, logical…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

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…

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…

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…

Fuzzing is an effective bug-finding technique but it struggles with complex systems like JavaScript engines that demand precise grammatical input. Recently, researchers have adopted language models for context-aware mutation in fuzzing to…

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…

A fundamental problem in cybersecurity and computer science is determining whether a program is free of bugs and vulnerabilities. Fuzzing, a popular approach to discovering vulnerabilities in programs, has several advantages over…

Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique ``jailbreak prompt'' can circumvent safety-aligned measures and induce LLMs to output malicious content.…