相关论文: Same Model, Different Weakness: How Language and M…

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent understanding. We introduce CSR-Bench, a benchmark for…

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…

Multimodal Large Language Models (MLLMs), which integrate vision and other modalities into Large Language Models (LLMs), significantly enhance AI capabilities but also introduce new security vulnerabilities. By exploiting the…

Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat modelling, prior work has primarily evaluated a number of general-purpose Large Language Models…

The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fixed template between the input instruction and initial model…

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…

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…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

The robustness and security of large language models (LLMs) has become a prominent research area. One notable vulnerability is the ability to bypass LLM safeguards by translating harmful queries into rare or underrepresented languages, a…

The recent boom and rapid integration of Large Language Models (LLMs) into a wide range of applications warrants a deeper understanding of their security and safety vulnerabilities. This paper presents a comparative analysis of the…

The pursuit of leaderboard rankings in Large Language Models (LLMs) has created a fundamental paradox: models excel at standardized tests while failing to demonstrate genuine language understanding and adaptability. Our systematic analysis…

Building safe Large Language Models (LLMs) across multiple languages is essential in ensuring both safe access and linguistic diversity. To this end, we conduct a large-scale, comprehensive safety evaluation of the current LLM landscape.…

The integration of new modalities enhances the capabilities of multimodal large language models (MLLMs) but also introduces additional vulnerabilities. In particular, simple visual jailbreaking attacks can manipulate open-source MLLMs more…

Large Language Models (LLMs) undergo continuous updates to improve user experience. However, prior research on the security and safety implications of LLMs has primarily focused on their specific versions, overlooking the impact of…

We investigate long-context vulnerabilities in Large Language Models (LLMs) through Many-Shot Jailbreaking (MSJ). Our experiments utilize context length of up to 128K tokens. Through comprehensive analysis with various many-shot attack…

Jailbreaking in Large Language Models (LLMs) threatens their safe use in sensitive domains like education by allowing users to bypass ethical safeguards. This study focuses on detecting jailbreaks in 2-Sigma, a clinical education platform…

Large language models have drawn significant attention to the challenge of safe alignment, especially regarding jailbreak attacks that circumvent security measures to produce harmful content. To address the limitations of existing methods…

Linguistically inclusive LLMs -- which maintain good performance regardless of the language with which they are prompted -- are necessary for the diffusion of AI benefits around the world. Multilingual jailbreaks that rely on language…