English
Related papers

Related papers: Targeted Downstream-Agnostic Attack

200 papers

Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective encoders using a large volume of unlabeled data, leading to…

Cryptography and Security · Computer Science 2022-07-21 Yupei Liu , Jinyuan Jia , Hongbin Liu , Neil Zhenqiang Gong

Despite their impressive performance, deep neural networks (DNNs) are widely known to be vulnerable to adversarial attacks, which makes it challenging for them to be deployed in security-sensitive applications, such as autonomous driving.…

Machine Learning · Computer Science 2020-10-09 Philipp Benz , Chaoning Zhang , Tooba Imtiaz , In So Kweon

Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to defend against such attacks remains an open problem. We…

Machine Learning · Statistics 2021-02-01 Matthew Willetts , Alexander Camuto , Tom Rainforth , Stephen Roberts , Chris Holmes

Recent studies have revealed that text-to-image diffusion models are vulnerable to backdoor attacks, where attackers implant stealthy textual triggers to manipulate model outputs. Previous backdoor detection methods primarily focus on the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Zhongqi Wang , Jie Zhang , Shiguang Shan , Xilin Chen

Recent work has highlighted the vulnerability of many deep machine learning models to adversarial examples. It attracts increasing attention to adversarial attacks, which can be used to evaluate the security and robustness of models before…

Machine Learning · Computer Science 2020-06-22 Xuli Sun , Shiliang Sun

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 2023-11-09 Thibault Simonetto , Salah Ghamizi , Antoine Desjardins , Maxime Cordy , Yves Le Traon

Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Arjhun Swaminathan , Mete Akgün

With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…

Computation and Language · Computer Science 2019-04-12 Wei Emma Zhang , Quan Z. Sheng , Ahoud Alhazmi , Chenliang Li

Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Zhan Li , Mingyu Zhao , Xin Dong , Haibin Ling , Bingyao Huang

Recent works have demonstrated convolutional neural networks are vulnerable to adversarial examples, i.e., inputs to machine learning models that an attacker has intentionally designed to cause the models to make a mistake. To improve the…

Computer Vision and Pattern Recognition · Computer Science 2020-05-12 Xianxu Hou , Jingxin Liu , Bolei Xu , Xiaolong Wang , Bozhi Liu , Guoping Qiu

Pre-trained language models of code are now widely used in various software engineering tasks such as code generation, code completion, vulnerability detection, etc. This, in turn, poses security and reliability risks to these models. One…

Software Engineering · Computer Science 2024-11-01 Thanh-Dat Nguyen , Yang Zhou , Xuan Bach D. Le , Patanamon Thongtanunam , David Lo

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream…

Cryptography and Security · Computer Science 2021-08-03 Jinyuan Jia , Yupei Liu , Neil Zhenqiang Gong

Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its…

Cryptography and Security · Computer Science 2021-08-16 Yuezun Li , Yiming Li , Baoyuan Wu , Longkang Li , Ran He , Siwei Lyu

Pre-trained encoders available online have been widely adopted to build downstream machine learning (ML) services, but various attacks against these encoders also post security and privacy threats toward such a downstream ML service…

Machine Learning · Computer Science 2025-05-27 Shaopeng Fu , Xuexue Sun , Ke Qing , Tianhang Zheng , Di Wang

Deep neural networks have achieved impressive performance in various areas, but they are shown to be vulnerable to adversarial attacks. Previous works on adversarial attacks mainly focused on the single-task setting. However, in real…

Machine Learning · Computer Science 2020-11-20 Pengxin Guo , Yuancheng Xu , Baijiong Lin , Yu Zhang

The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness. However, the progress is usually hampered by insufficient robustness evaluations. As…

Machine Learning · Computer Science 2021-10-19 Xiao Yang , Yinpeng Dong , Wenzhao Xiang , Tianyu Pang , Hang Su , Jun Zhu

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Cryptography and Security · Computer Science 2024-10-14 Xiaopei Zhu , Peiyang Xu , Guanning Zeng , Yingpeng Dong , Xiaolin Hu

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, namely, AEs generated for a source model fool other (target) models. In this paper, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2022-09-08 Miki Tanaka , Isao Echizen , Hitoshi Kiya

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Chenyu Zhang , Lanjun Wang , Anan Liu

Systems based on deep neural networks are vulnerable to adversarial attacks. Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Zihao Pan , Lifeng Chen , Weibin Wu , Yuhang Cao , Zibin Zheng