Related papers: Precise Shield: Explaining and Aligning VLLM Safet…

The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate the finetuning process, resulting in an alignment-broken…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved through post-training methods, which are computationally…

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…

Despite emerging efforts to enhance the safety of Vision-Language Models (VLMs), current approaches face two main shortcomings. 1) Existing safety-tuning datasets and benchmarks only partially consider how image-text interactions can yield…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Vision Language Models (VLMs) hold great promise for streamlining labour-intensive medical imaging workflows, yet systematic security evaluations in clinical settings remain scarce. We introduce VSF--Med, an end-to-end vulnerability-scoring…

Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages but also exhibit an imbalance in multilingual capabilities. In this work, we delve into the…

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

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…

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated…

Large Vision-Language Models (LVLMs) excel in diverse cross-modal tasks. However, object hallucination, where models produce plausible but inaccurate object descriptions, remains a significant challenge. In contrast to previous work…

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Vision-language alignment in Large Vision-Language Models (LVLMs) successfully enables LLMs to understand visual input. However, we find that existing vision-language alignment methods fail to transfer the existing safety mechanism for text…

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture.…