English
Related papers

Related papers: Adversarial Attacks against Closed-Source MLLMs vi…

200 papers

Adversarial perturbations can mislead Multimodal Large Language Models (MLLMs) recognize a benign image as a specific target object, posing serious risks in safety-critical scenarios such as autonomous driving and medical diagnosis. This…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Haobo Wang , Xiaorong Ma , Weiqi Luo , Xiaojun Jia , Jiwu Huang

Vision-language pre-training (VLP) models demonstrate impressive abilities in processing both images and text. However, they are vulnerable to multi-modal adversarial examples (AEs). Investigating the generation of high-transferability…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Dongchen Han , Xiaojun Jia , Yang Bai , Jindong Gu , Yang Liu , Xiaochun Cao

Targeted adversarial attacks on closed-source multimodal large language models (MLLMs) have been increasingly explored under black-box transfer, yet prior methods are predominantly sample-specific and offer limited reusability across…

Artificial Intelligence · Computer Science 2026-04-21 Hui Lu , Yi Yu , Yiming Yang , Chenyu Yi , Xueyi Ke , Qixing Zhang , Bingquan Shen , Alex Kot , Xudong Jiang

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yuanbo Li , Tianyang Xu , Cong Hu , Tao Zhou , Xiao-Jun Wu , Josef Kittler

Transferable adversarial attack has drawn increasing attention due to their practical threaten to real-world applications. In particular, the feature-level adversarial attack is one recent branch that can enhance the transferability via…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Xianglong , Yuezun Li , Haipeng Qu , Junyu Dong

Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to adversarial examples. While prior efforts focus on improving the adversarial transferability…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Xin Liu , Aoyang Zhou , Aoyang Zhou

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

Multimodal Large Language Models (MLLMs) demonstrate exceptional performance in cross-modality interaction, yet they also suffer adversarial vulnerabilities. In particular, the transferability of adversarial examples remains an ongoing…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Hao Cheng , Erjia Xiao , Jiayan Yang , Jinhao Duan , Yichi Wang , Jiahang Cao , Qiang Zhang , Le Yang , Kaidi Xu , Jindong Gu , Renjing Xu

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Peng Xie , Yequan Bie , Jianda Mao , Yangqiu Song , Yang Wang , Hao Chen , Kani Chen

The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against…

Cryptography and Security · Computer Science 2025-11-21 Yijun Yang , Lichao Wang , Jianping Zhang , Chi Harold Liu , Lanqing Hong , Qiang Xu

With the great advancements in large language models (LLMs), adversarial attacks against LLMs have recently attracted increasing attention. We found that pre-existing adversarial attack methodologies exhibit limited transferability and are…

Computation and Language · Computer Science 2024-09-10 Zelin Li , Kehai Chen , Lemao Liu , Xuefeng Bai , Mingming Yang , Yang Xiang , Min Zhang

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained attention for their capabilities in image recognition and understanding. However, while MLLMs are vulnerable to adversarial attacks, the transferability of…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Chenhe Gu , Jindong Gu , Andong Hua , Yao Qin

Adversarial examples have revealed the vulnerability of deep learning models and raised serious concerns about information security. The transfer-based attack is a hot topic in black-box attacks that are practical to real-world scenarios…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Jian-Wei Li , Wen-Ze Shao

Current adversarial attacks for evaluating the robustness of vision-language pre-trained (VLP) models in multi-modal tasks suffer from limited transferability, where attacks crafted for a specific model often struggle to generalize…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Peng-Fei Zhang , Guangdong Bai , Zi Huang

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Jingwen Ye , Ruonan Yu , Songhua Liu , Xinchao Wang

Deep neural networks are susceptible to adversarial attacks, which pose a significant threat to their security and reliability in real-world applications. The most notable adversarial attacks are transfer-based attacks, where an adversary…

Computer Vision and Pattern Recognition · Computer Science 2023-11-02 Kunyu Wang , Juluan Shi , Wenxuan Wang

Adversarial attacks in black-box settings are highly practical, with transfer-based attacks being the most effective at generating adversarial examples (AEs) that transfer from surrogate models to unseen target models. However, their…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Tao Wu , Tie Luo

Despite the remarkable performance of vision language models (VLMs) such as Contrastive Language Image Pre-training (CLIP), the large size of these models is a considerable obstacle to their use in federated learning (FL) systems where the…

Machine Learning · Computer Science 2025-03-11 Yihang Wu , Ahmad Chaddad , Christian Desrosiers , Tareef Daqqaq , Reem Kateb

Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of adversarial examples, including advanced optimization, data…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Zhaoyu Chen , Haijing Guo , Kaixun Jiang , Jiyuan Fu , Xinyu Zhou , Dingkang Yang , Hao Tang , Bo Li , Wenqiang Zhang

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

Machine Learning · Computer Science 2022-05-20 Thomas Cilloni , Charles Walter , Charles Fleming
‹ Prev 1 2 3 10 Next ›