English
Related papers

Related papers: Adversarial Attacks Against MLLMs via Progressive …

200 papers

We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a…

Machine Learning · Computer Science 2020-07-28 Shuyu Cheng , Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

Deep networks are highly vulnerable to adversarial attacks, yet conventional attack methods utilize static adversarial perturbations that induce fixed mispredictions. In this work, we exploit an overlooked property of adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Yaoteng Tan , Zikui Cai , M. Salman Asif

Language-conditioned robotic learning has significantly enhanced robot adaptability by enabling a single model to execute diverse tasks in response to verbal commands. Despite these advancements, security vulnerabilities within this domain…

Machine Learning · Computer Science 2024-11-26 Ke Zhao , Huayang Huang , Miao Li , Yu Wu

Multimodal embeddings serve as a bridge for aligning vision and language, with the two primary implementations -- CLIP-based and MLLM-based embedding models -- both limited to capturing only global semantic information. Although numerous…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Lexiang Hu , Youze Xue , Dian Li , Gang Liu , Zhouchen Lin

This work aims to investigate how different Large Language Models (LLMs) alignment methods affect the models' responses to prompt attacks. We selected open source models based on the most common alignment methods, namely, Supervised…

Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Ziwen He , Wei Wang , Jing Dong , Tieniu Tan

Adversarial examples pose significant threats to deep neural networks (DNNs), and their property of transferability in the black-box setting has led to the emergence of transfer-based attacks, making it feasible to target real-world…

Computer Vision and Pattern Recognition · Computer Science 2025-07-23 Yuyang Luo , Xiaosen Wang , Zhijin Ge , Yingzhe He

Autonomous driving (AD) is evolving towards end-to-end (E2E) frameworks through two primary paradigms: monolithic models exemplified by Vision-Language-Action (VLA), and specialized modular architectures. Despite their divergent designs,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Xinyu Zeng , Xiangkun He , Lei Tao , Chen Lv , Hong Cheng

This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Yiwen Guo , Qizhang Li , Wangmeng Zuo , Hao Chen

Adversarial patch attacks can fool the face recognition (FR) models via small patches. However, previous adversarial patch attacks often result in unnatural patterns that are easily noticeable. Generating transferable and stealthy…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Yanjie Li , Mingxing Duan , Xuelong Dai , Bin Xiao

As Contrastive Language-Image Pre-training (CLIP) models are increasingly adopted for diverse downstream tasks and integrated into large vision-language models (VLMs), their susceptibility to adversarial perturbations has emerged as a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Hanxun Huang , Sarah Erfani , Yige Li , Xingjun Ma , James Bailey

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

Multiagent Systems · Computer Science 2025-10-10 Rana Muhammad Shahroz Khan , Zhen Tan , Sukwon Yun , Charles Fleming , Tianlong Chen

To circumvent the alignment of large language models (LLMs), current optimization-based adversarial attacks usually craft adversarial prompts by maximizing the likelihood of a so-called affirmative response. An affirmative response is a…

Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Sen Nie , Jie Zhang , Jianxin Yan , Shiguang Shan , Xilin Chen

Deep neural networks can be vulnerable to adversarially crafted examples, presenting significant risks to practical applications. A prevalent approach for adversarial attacks relies on the transferability of adversarial examples, which are…

Information Retrieval · Computer Science 2024-11-12 Shanjun Xu , Linghui Li , Kaiguo Yuan , Bingyu Li

The protection of Intellectual Property (IP) for Large Language Models (LLMs) has become a critical concern as model theft and unauthorized commercialization escalate. While adversarial fingerprinting offers a promising black-box solution…

Cryptography and Security · Computer Science 2026-05-28 Zhebo Wang , Zhenhua Xu , Maike Li , Wenpeng Xing , Chunqiang Hu , Chen Zhi , Meng Han

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Jiaming Zhang , Xingjun Ma , Xin Wang , Lingyu Qiu , Jiaqi Wang , Yu-Gang Jiang , Jitao Sang

The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…

Artificial Intelligence · Computer Science 2024-12-18 Yifan Yang , Qiao Jin , Furong Huang , Zhiyong Lu

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…

Computation and Language · Computer Science 2023-06-09 Lifan Yuan , Yichi Zhang , Yangyi Chen , Wei Wei

While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…

Computation and Language · Computer Science 2025-06-03 Danni Liu , Jan Niehues
‹ Prev 1 3 4 5 6 7 10 Next ›