Related papers: Refusal Direction is Universal Across Safety-Align…

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…

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies have been proposed to mitigate these threats, there has…

Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new…

Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this…

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.…

Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from…

Multilingual LLMs often have knowledge disparities across languages, with larger gaps in under-resourced languages. Teaching LLMs to abstain in the face of knowledge gaps is thus a promising strategy to mitigate hallucinations in…

Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative models. We introduce a novel fingerprinting framework that leverages the behavioral patterns…

As large language models (LLMs) are deployed globally, it is crucial that their responses are calibrated across languages to accurately convey uncertainty and limitations. Prior work shows that LLMs are linguistically overconfident in…

Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Safety-aligned large language models (LLMs) sometimes falsely refuse pseudo-harmful prompts, like "how to kill a mosquito," which are actually harmless. Frequent false refusals not only frustrate users but also provoke a public backlash…

Large Language Models (LLMs) are commonly evaluated for robustness against paraphrased or semantically equivalent jailbreak prompts, yet little attention has been paid to linguistic variation as an attack surface. In this work, we…

Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how…

The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that…

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Large Language Models (LLMs) are susceptible to malicious influence by cyber attackers through intrusions such as adversarial, backdoor, and embedding inversion attacks. In response, the burgeoning field of LLM Security aims to study and…

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues,…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing…