English
Related papers

Related papers: Mechanistic Understandings of Representation Vulne…

200 papers

Vision Transformers (ViTs) are increasingly used in computer vision due to their high performance, but their vulnerability to adversarial attacks is a concern. Existing methods lack a solid theoretical basis, focusing mainly on empirical…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Xixu Hu , Runkai Zheng , Jindong Wang , Cheuk Hang Leung , Qi Wu , Xing Xie

The ability of deep neural networks (DNNs) come from extracting and interpreting features from the data provided. By exploiting intermediate features in DNNs instead of relying on hard labels, we craft adversarial perturbation that…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Shangbo Wu , Yu-an Tan , Ruinan Ma , Wencong Ma , Dehua Zhu , Yuanzhang Li

Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures. Existing works empower the models by massive data, such as large-scale pre-training…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Xiangning Chen , Cho-Jui Hsieh , Boqing Gong

Vision Transformers (ViTs) have become prominent models for solving various vision tasks. However, the interpretability of ViTs has not kept pace with their promising performance. While there has been a surge of interest in developing {\it…

Computer Vision and Pattern Recognition · Computer Science 2025-05-02 Yao Qiang , Chengyin Li , Prashant Khanduri , Dongxiao Zhu

Patch attacks, one of the most threatening forms of physical attack in adversarial examples, can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous region. Certifiable patch defense can guarantee…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Zhaoyu Chen , Bo Li , Jianghe Xu , Shuang Wu , Shouhong Ding , Wenqiang Zhang

Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Srinadh Bhojanapalli , Ayan Chakrabarti , Daniel Glasner , Daliang Li , Thomas Unterthiner , Andreas Veit

As deep learning models increasingly find applications in critical domains such as medical imaging, the need for transparent and trustworthy decision-making becomes paramount. Many explainability methods provide insights into how these…

Computer Vision and Pattern Recognition · Computer Science 2023-11-09 Piotr Komorowski , Hubert Baniecki , Przemysław Biecek

Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To mitigate these vulnerabilities, adversarial training and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Francesco Villani , Igor Maljkovic , Dario Lazzaro , Angelo Sotgiu , Antonio Emanuele Cinà , Fabio Roli

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Jiawei Yang , Katie Z Luo , Jiefeng Li , Congyue Deng , Leonidas Guibas , Dilip Krishnan , Kilian Q Weinberger , Yonglong Tian , Yue Wang

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with…

Cryptography and Security · Computer Science 2024-01-08 Ryota Iijima , Sayaka Shiota , Hitoshi Kiya

With the perpetual increase of complexity of the state-of-the-art deep neural networks, it becomes a more and more challenging task to maintain their interpretability. Our work aims to evaluate the effects of adversarial training utilized…

Computer Vision and Pattern Recognition · Computer Science 2023-11-21 Delyan Boychev

Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to…

Machine Learning · Computer Science 2025-10-14 Edward Stevinson , Lucas Prieto , Melih Barsbey , Tolga Birdal

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Yuanduo Hong , Huihui Pan , Weichao Sun , Xinghu Yu , Huijun Gao

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Computation and Language · Computer Science 2022-10-28 Jiahao Zhao , Wenji Mao

Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly…

Computer Vision and Pattern Recognition · Computer Science 2022-07-12 Ting Yao , Yingwei Pan , Yehao Li , Chong-Wah Ngo , Tao Mei

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

Despite their tremendous success in modelling high-dimensional data manifolds, deep neural networks suffer from the threat of adversarial attacks - Existence of perceptually valid input-like samples obtained through careful perturbation…

Computer Vision and Pattern Recognition · Computer Science 2019-09-09 Vinay Kyatham , Mayank Mishra , Tarun Kumar Yadav , Deepak Mishra , Prathosh AP

The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input…

Computer Vision and Pattern Recognition · Computer Science 2019-06-17 Houpu Yao , Zhe Wang , Guangyu Nie , Yassine Mazboudi , Yezhou Yang , Yi Ren

Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Jingjie He , Weijie Liang , Zihan Shan , Matthew Caesar

Vision transformers (ViTs) have demonstrated impressive performance in various computer vision tasks. However, the adversarial examples generated by ViTs are challenging to transfer to other networks with different structures. Recent attack…

Computer Vision and Pattern Recognition · Computer Science 2022-04-28 Huipeng Zhou , Yu-an Tan , Yajie Wang , Haoran Lyu , Shangbo Wu , Yuanzhang Li