Related papers: Bootstrapping LLM Robustness for VLM Safety via Re…

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities. However, more modalities bring more vulnerabilities to being utilized for jailbreak…

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy…

Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual…

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

Recent advancements in multimodal techniques open exciting possibilities for models excelling in diverse tasks involving text, audio, and image processing. Models like GPT-4V, blending computer vision and language modeling, excel in complex…

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks. However, due to their inherent vulnerability and…

Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual…

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success…

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

The robust safety of Vision-Language Large Models (VLLMs) against joint multilingual and multimodal threats remains severely underexplored. Current benchmarks typically isolate these dimensions, being either multilingual but text-only, or…

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

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…

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

This paper introduces LlavaGuard, a suite of VLM-based vision safeguards that address the critical need for reliable guardrails in the era of large-scale data and models. To this end, we establish a novel open framework, describing a…

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…