English
Related papers

Related papers: Memory Efficient Full-gradient Attacks (MEFA) Fram…

200 papers

Deep neural networks perform remarkably well on image classification tasks but remain vulnerable to carefully crafted adversarial perturbations. This work revisits linear dimensionality reduction as a simple, data-adapted defense. We…

Machine Learning · Computer Science 2025-10-08 Killian Steunou , Théo Druilhe , Sigurd Saue

Defense models against adversarial attacks have grown significantly, but the lack of practical evaluation methods has hindered progress. Evaluation can be defined as looking for defense models' lower bound of robustness given a budget…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Ye Liu , Yaya Cheng , Lianli Gao , Xianglong Liu , Qilong Zhang , Jingkuan Song

The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications. In this paper, we propose a randomized diversification as a defense strategy. We introduce a multi-channel architecture in a…

Machine Learning · Computer Science 2019-04-02 Olga Taran , Shideh Rezaeifar , Taras Holotyak , Slava Voloshynovskiy

Effective defense of deep neural networks against adversarial attacks remains a challenging problem, especially under powerful white-box attacks. In this paper, we develop a new method called ensemble generative cleaning with feedback loops…

Computer Vision and Pattern Recognition · Computer Science 2020-04-24 Jianhe Yuan , Zhihai He

Recent optical flow methods are almost exclusively judged in terms of accuracy, while their robustness is often neglected. Although adversarial attacks offer a useful tool to perform such an analysis, current attacks on optical flow methods…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Jenny Schmalfuss , Philipp Scholze , Andrés Bruhn

Deep neural networks are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to original images. Most existing adversarial attack methods achieve nearly 100% attack success rates under the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-15 Guoqiu Wang , Huanqian Yan , Ying Guo , Xingxing Wei

Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance the performance of…

Artificial Intelligence · Computer Science 2024-09-23 Zhibo Jin , Jiayu Zhang , Zhiyu Zhu , Chenyu Zhang , Jiahao Huang , Jianlong Zhou , Fang Chen

State-of-the-art deep learning models for tabular data have recently achieved acceptable performance to be deployed in industrial settings. However, the robustness of these models remains scarcely explored. Contrary to computer vision,…

Machine Learning · Computer Science 2024-06-05 Thibault Simonetto , Salah Ghamizi , Maxime Cordy

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performance. To address this…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Long Xu , Peng Gao , Wen-Jia Tang , Fei Wang , Ru-Yue Yuan

Convolutional Neural Networks have achieved significant success across multiple computer vision tasks. However, they are vulnerable to carefully crafted, human-imperceptible adversarial noise patterns which constrain their deployment in…

Computer Vision and Pattern Recognition · Computer Science 2020-01-08 Aamir Mustafa , Salman H. Khan , Munawar Hayat , Jianbing Shen , Ling Shao

This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Raz Lapid , Almog Dubin , Moshe Sipper

Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the…

Machine Learning · Computer Science 2021-11-03 Kaleel Mahmood , Deniz Gurevin , Marten van Dijk , Phuong Ha Nguyen

Feature transformation aims to generate new pattern-discriminative feature space from original features to improve downstream machine learning (ML) task performances. However, the discrete search space for the optimal feature explosively…

Machine Learning · Computer Science 2023-09-26 Dongjie Wang , Meng Xiao , Min Wu , Pengfei Wang , Yuanchun Zhou , Yanjie Fu

Adversarial attacks have the potential to mislead deep neural network classifiers by introducing slight perturbations. Developing algorithms that can mitigate the effects of these attacks is crucial for ensuring the safe use of artificial…

Machine Learning · Computer Science 2023-10-31 Boya Zhang , Weijian Luo , Zhihua Zhang

The reliance on deep learning algorithms has grown significantly in recent years. Yet, these models are highly vulnerable to adversarial attacks, which introduce visually imperceptible perturbations into testing data to induce…

Machine Learning · Computer Science 2019-06-14 Rajeev Sahay , Rehana Mahfuz , Aly El Gamal

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

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

Machine Learning · Computer Science 2024-09-09 Hanbin Hong , Xinyu Zhang , Binghui Wang , Zhongjie Ba , Yuan Hong

Boundary based blackbox attack has been recognized as practical and effective, given that an attacker only needs to access the final model prediction. However, the query efficiency of it is in general high especially for high dimensional…

Machine Learning · Computer Science 2021-06-14 Jiawei Zhang , Linyi Li , Huichen Li , Xiaolu Zhang , Shuang Yang , Bo Li

Persistent memory attacks against LLM agents achieve high attack success rates against open-source models. In these attacks, malicious instructions injected via RAG-retrieved documents are stored in persistent memory and executed in later…

Cryptography and Security · Computer Science 2026-05-12 Jun Wen Leong

Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a…

Machine Learning · Computer Science 2020-05-19 MaungMaung AprilPyone , Hitoshi Kiya