Related papers: Cross-Modal Safety Alignment: Is textual unlearnin…

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

Vision-language pretraining (VLP) with transformers has demonstrated exceptional performance across numerous multimodal tasks. However, the adversarial robustness of these models has not been thoroughly investigated. Existing multimodal…

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…

This research paper addresses the challenge of modality mismatch in multimodal learning, where the modalities available during inference differ from those available at training. We propose the Text-centric Alignment for Multi-Modality…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Recent research looks to harness the general knowledge and reasoning of large language models (LLMs) into agents that accomplish user-specified goals in interactive environments. Vision-language models (VLMs) extend LLMs to multi-modal data…

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…

Augmenting Large Language Models (LLMs) with image-understanding capabilities has resulted in a boom of high-performing Vision-Language models (VLMs). While studying the alignment of LLMs to human values has received widespread attention,…

Vision-Language Models (VLMs) have demonstrated immense capabilities in multi-modal understanding and inference tasks such as Visual Question Answering (VQA), which requires models to infer outputs based on visual and textual context…

The emergence of vision language models (VLMs) comes with increased safety concerns, as the incorporation of multiple modalities heightens vulnerability to attacks. Although VLMs can be built upon LLMs that have textual safety alignment, it…

Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On…

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

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…

Recently, vision-language pretraining has emerged as a transformative technique that integrates the strengths of both visual and textual modalities, resulting in powerful vision-language models (VLMs). Leveraging web-scale pretraining data,…

The increasing integration of Visual Language Models (VLMs) into AI systems necessitates robust model alignment, especially when handling multimodal content that combines text and images. Existing evaluation datasets heavily lean towards…

As the influence of large language models (LLMs) spans across global communities, their safety challenges in multilingual settings become paramount for alignment research. This paper examines the variations in safety challenges faced by…

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the…

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations. In this paper, we begin with…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…