Related papers: PRISM: Robust VLM Alignment with Principled Reason…

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish…

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

The emergence of Multimodal Large Language Models (MLRMs) has enabled sophisticated visual reasoning capabilities by integrating reinforcement learning and Chain-of-Thought (CoT) supervision. However, while these enhanced reasoning…

Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities…

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…

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…

As large language models evolve, Machine Unlearning has emerged to address growing concerns around user privacy, copyright infringement, and overall safety. Yet state-of-the-art (SOTA) unlearning methods often suffer from catastrophic…

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing…

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…

Large vision-language models (LVLMs) are increasingly deployed in globally distributed applications, such as tourism assistants, yet their ability to produce culturally appropriate responses remains underexplored. Existing multimodal safety…

We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before generating its final response. Unlike existing safety alignment methods that optimize only for…

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These…

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Vision-Language Models (VLMs) have remarkable abilities in generating multimodal reasoning tasks. However, potential misuse or safety alignment concerns of VLMs have increased significantly due to different categories of attack vectors.…

Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this…

A critical gap exists between the general-purpose visual understanding of state-of-the-art physical AI models and the specialized perceptual demands of structured real-world deployment environments. We present PRISM, a 270K-sample…

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…

Reasoning Language Models (RLMs) have gained traction for their ability to perform complex, multi-step reasoning tasks through mechanisms such as Chain-of-Thought (CoT) prompting or fine-tuned reasoning traces. While these capabilities…

In this work, we propose Perspective Reasoning for Integrated Synthesis and Mediation (PRISM), a multiple-perspective framework for addressing persistent challenges in AI alignment such as conflicting human values and specification gaming.…