English
Related papers

Related papers: Grounding-Driven Attack: Improving Encoder-based A…

200 papers

Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to downstream-agnostic attacks (DAAs). Existing DAA methods operate under a permissive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zhuxin Lei , Ziyuan Yang , Yi Zhang

Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision and language tasks. Several recent works, however, showed…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 Navid Rajabi , Jana Kosecka

Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood. Existing interpretability work on VLMs uses Sparse Autoencoders (SAEs), which decompose…

Machine Learning · Computer Science 2026-05-25 Dimitrios Damianos , Leon Voukoutis , Georgios Skyrianos , Vassilis Katsouros , Georgios Paraskevopoulos

The success of adversarial attacks to speaker recognition is mainly in white-box scenarios. When applying the adversarial voices that are generated by attacking white-box surrogate models to black-box victim models, i.e.…

Sound · Computer Science 2023-02-22 Jiadi Yao , Hong Luo , Xiao-Lei Zhang

Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Woo Jae Kim , Seunghoon Hong , Sung-Eui Yoon

Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adversarial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Bohan Liu , Xiaosen Wang

Vision transformers (ViTs) have been successfully deployed in a variety of computer vision tasks, but they are still vulnerable to adversarial samples. Transfer-based attacks use a local model to generate adversarial samples and directly…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Jianping Zhang , Yizhan Huang , Weibin Wu , Michael R. Lyu

Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Chenyang Li , Wenbing Tang , Yihao Huang , Sinong Simon Zhan , Ming Hu , Xiaojun Jia , Yang Liu

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Shangbo Wu , Yu-an Tan , Yajie Wang , Ruinan Ma , Wencong Ma , Yuanzhang Li

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zhiqiang Wang , Dongrui Liu , Yan Li , Zonghao Ying , Wei Xue , Wenhan Luo , Yike Guo

Recent advances in instruction tuning have led to the development of State-of-the-Art Large Multimodal Models (LMMs). Given the novelty of these models, the impact of visual adversarial attacks on LMMs has not been thoroughly examined. We…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xuanming Cui , Alejandro Aparcedo , Young Kyun Jang , Ser-Nam Lim

While Vision-Language-Action (VLA) models have emerged as powerful generalist policies, their severe vulnerability to adversarial patches significantly hinders their deployment in safety-critical domains. Moreover, existing patch attacks…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Jiyuan Fu , Kaixun Jiang , Jingkai Jia , Zhaoyu Chen , Xueyao Chen , Lingyi Hong , Shuyong Gao , Chenzhi Tan , Dingkang Yang , Wenqiang Zhang

Large language models (LLMs) have demonstrated impressive performance across various domains but remain susceptible to safety concerns. Prior research indicates that gradient-based adversarial attacks are particularly effective against…

Computation and Language · Computer Science 2024-10-30 Jingbo Su

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Ravikumar Balakrishnan , Sanket Mendapara , Ankit Garg

Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to closed-source MLLMs. A key challenge for improving adversarial…

Cryptography and Security · Computer Science 2026-05-22 Leitao Yuan , Qinghua Mao , Daizong Liu , Kun Wang , Wenjie Wang , Yan Teng , Jing Shao , Dongrui Liu

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Meiwen Ding , Song Xia , Chenqi Kong , Xudong Jiang

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Yiyang Huang , Liang Shi , Yitian Zhang , Yi Xu , Yun Fu

Gradient-based adversarial prompting, such as the Greedy Coordinate Gradient (GCG) algorithm, has emerged as a powerful method for jailbreaking large language models (LLMs). In this paper, we present a systematic appraisal of GCG and its…

Computation and Language · Computer Science 2025-09-03 Yuting Tan , Xuying Li , Zhuo Li , Huizhen Shu , Peikang Hu

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial…

Cryptography and Security · Computer Science 2024-02-07 Ziyi Yin , Muchao Ye , Tianrong Zhang , Tianyu Du , Jinguo Zhu , Han Liu , Jinghui Chen , Ting Wang , Fenglong Ma

Recent studies on AI security have highlighted the vulnerability of Vision-Language Pre-training (VLP) models to subtle yet intentionally designed perturbations in images and texts. Investigating multimodal systems' robustness via…

Computer Vision and Pattern Recognition · Computer Science 2024-08-07 Haonan Zheng , Wen Jiang , Xinyang Deng , Wenrui Li