相关论文: ProGuard: Towards Proactive Multimodal Safeguard

The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and collaborative reasoning. However, these interactions create new security risks that…

We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal…

Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response patterns that are unforeseen by model developers. We systematically study whether LLM…

Social platforms have revolutionized information sharing, but also accelerated the dissemination of harmful and policy-violating content. To ensure safety and compliance at scale, moderation systems must go beyond efficiency and offer…

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single…

Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against the risk of policy-violating content, system-level moderation…

As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and harmful requests while upholding appropriate censorship boundaries has never been greater.…

State-of-the-art image classifiers trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental distribution shifts. On the other hand, several recent classifiers with…

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Reliable zero-shot detection of out-of-distribution (OOD) inputs is critical for deploying vision-language models in open-world settings. However, the lack of labeled negatives in zero-shot OOD detection necessitates proxy signals that…

Out-of-distribution (OOD) detection seeks to identify samples from unknown classes, a critical capability for deploying machine learning models in open-world scenarios. Recent research has demonstrated that Vision-Language Models (VLMs) can…

Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature. However, the field currently lacks a unified,…

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

While the safety risks of image-based large language models (Image LLMs) have been extensively studied, their video-based counterparts (Video LLMs) remain critically under-examined. To systematically study this problem, we introduce…

Out-of-distribution (OOD) robustness is a critical challenge for modern machine learning systems, particularly as they increasingly operate in multimodal settings involving inputs like video, audio, and sensor data. Currently, many OOD…

Detecting out-of-distribution (OOD) samples is important for deploying machine learning models in safety-critical applications such as autonomous driving and robot-assisted surgery. Existing research has mainly focused on unimodal scenarios…

With the rapid development of generative technology, current generative models can generate high-fidelity digital content and edit it in a controlled manner. However, there is a risk that malicious individuals might misuse these…

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…