Related papers: Seeing the Threat: Vulnerabilities in Vision-Langu…
The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol…
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…
Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…
Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…
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…
With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…
Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…
The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…
Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…
Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal perception and generation, yet their safety alignment remains a critical challenge.Existing defenses and vulnerable to multimodal jailbreaks, as visual…
Large Vision-Language Models (LVLMs) have demonstrated their powerful multimodal capabilities. However, they also face serious safety problems, as adversaries can induce robustness issues in LVLMs through the use of well-designed…
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for…
As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…
The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution. Nevertheless, these LLMs exhibit a notable limitation, as they are primarily adept at processing textual information. To address this…
The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…
Research in ML4VIS investigates how to use machine learning (ML) techniques to generate visualizations, and the field is rapidly growing with high societal impact. However, as with any computational pipeline that employs ML processes,…
Large-scale Video Foundation Models (VFMs) has significantly advanced various video-related tasks, either through task-specific models or Multi-modal Large Language Models (MLLMs). However, the open accessibility of VFMs also introduces…
As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…
Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…