Related papers: V-Attack: Targeting Disentangled Value Features fo…

Large Vision-Language Models (LVLMs), trained on multimodal big datasets, have significantly advanced AI by excelling in vision-language tasks. However, these models remain vulnerable to adversarial attacks, particularly jailbreak attacks,…

While DeepFake applications are becoming popular in recent years, their abuses pose a serious privacy threat. Unfortunately, most related detection algorithms to mitigate the abuse issues are inherently vulnerable to adversarial attacks…

Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of transferable AEs, which succeed across unseen models, is key to…

Voice anonymization systems aim to protect speaker privacy by obscuring vocal traits while preserving the linguistic content relevant for downstream applications. However, because these linguistic cues remain intact, they can be exploited…

Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their applications become increasingly widespread, recent studies have revealed that VLMs are…

Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the attack surface of prompt injection. Despite this growing concern, existing attacks still…

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single,…

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

Despite recent success on various tasks, deep learning techniques still perform poorly on adversarial examples with small perturbations. While optimization-based methods for adversarial attacks are well-explored in the field of computer…

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversarial image…

Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attacks attempt to extend VLM output sequences by optimizing…

Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal…

The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…

Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they are becoming increasingly prevalent, ensuring their robustness against adversarial attacks is paramount. This work…

Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible…

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is especially pronounced…

3D Vision-Language Models (VLMs), such as PointLLM and GPT4Point, have shown strong reasoning and generalization abilities in 3D understanding tasks. However, their adversarial robustness remains largely unexplored. Prior work in 2D VLMs…

Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elicit biased or malicious outputs. In this paper, we demonstrate…

Vision transformers (ViTs) process input images as sequences of patches via self-attention; a radically different architecture than convolutional neural networks (CNNs). This makes it interesting to study the adversarial feature space of…

In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks predominantly focus on the visual modality, perturbing solely…