相关论文: Cross-Modal Safety Mechanism Transfer in Large Vis…
Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…
Large visual-language models (LVLMs) integrate aligned large language models (LLMs) with visual modules to process multimodal inputs. However, the safety mechanisms developed for text-based LLMs do not naturally extend to visual modalities,…
Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to LLMs form Vision Language Models (VLMs). However, recent research shows that the visual modality in VLMs is highly…
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…
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this…
Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs) into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often compromises the inherent safety capabilities embedded in the original…
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…
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…
Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising performance, LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on…
Understanding the mechanisms behind Large Language Models (LLMs) is crucial for designing improved models and strategies. While recent studies have yielded valuable insights into the mechanisms of textual LLMs, the mechanisms of Multi-modal…
The deployment of multimodal large language models (MLLMs) has demonstrated remarkable success in engaging in conversations involving visual inputs, thanks to the superior power of large language models (LLMs). Those MLLMs are typically…
Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous…
Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs…
Currently, inspired by the success of vision-language models (VLMs), an increasing number of researchers are focusing on improving VLMs and have achieved promising results. However, most existing methods concentrate on optimizing the…
Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynamics, framing their inherent safety understanding in terms of…
Laboratories are prone to severe injuries from minor unsafe actions, yet continuous safety monitoring -- beyond mandatory pre-lab safety training -- is limited by human availability. Vision language models (VLMs) offer promise for…
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…
Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual…
Large Vision-Language Models (LVLMs) have achieved impressive performance across multimodal understanding and reasoning tasks, yet their internal safety mechanisms remain opaque and poorly controlled. In this work, we present a…
Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However, existing work has…