English
Related papers

Related papers: Certified Robustness to Adversarial Examples with …

200 papers

Deep Neural Networks are well known to be vulnerable to adversarial attacks and backdoor attacks, where minor modifications on the input are able to mislead the models to give wrong results. Although defenses against adversarial attacks…

Machine Learning · Computer Science 2022-08-01 Kaidi Jin , Tianwei Zhang , Chao Shen , Yufei Chen , Ming Fan , Chenhao Lin , Ting Liu

Self-supervised learning (SSL) has advanced significantly in visual representation learning, yet comprehensive evaluations of its adversarial robustness remain limited. In this study, we evaluate the adversarial robustness of seven…

Computer Vision and Pattern Recognition · Computer Science 2025-09-25 Ömer Veysel Çağatan , Ömer Faruk Tal , M. Emre Gürsoy

The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustness of learning algorithms against such attacks. Existing…

Machine Learning · Computer Science 2025-02-25 Avinandan Bose , Laurent Lessard , Maryam Fazel , Krishnamurthy Dj Dvijotham

How do we interpret the differential privacy (DP) guarantee for network data? We take a deep dive into a popular form of network DP ($\varepsilon$--edge DP) to find that many of its common interpretations are flawed. Drawing on prior work…

Statistics Theory · Mathematics 2025-04-18 Jonathan Hehir , Xiaoyue Niu , Aleksandra Slavkovic

The increasing availability of personal data has enabled significant advances in fields such as machine learning, healthcare, and cybersecurity. However, this data abundance also raises serious privacy concerns, especially in light of…

Cryptography and Security · Computer Science 2026-04-24 Napsu Karmitsa , Antti Airola , Tapio Pahikkala , Tinja Pitkämäki

Artificial intelligence (AI) has seen a tremendous surge in capabilities thanks to the use of foundation models trained on internet-scale data. On the flip side, the uncurated nature of internet-scale data also poses significant privacy and…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Yaodong Yu , Maziar Sanjabi , Yi Ma , Kamalika Chaudhuri , Chuan Guo

Malicious intelligent algorithms greatly threaten the security of social users' privacy by detecting and analyzing the uploaded photos to social network platforms. The destruction to DNNs brought by the adversarial attack sparks the…

Computer Vision and Pattern Recognition · Computer Science 2022-04-27 Jiawei Zhang , Jinwei Wang , Hao Wang , Xiangyang Luo

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples…

Machine Learning · Computer Science 2020-10-27 Huimin Zeng , Chen Zhu , Tom Goldstein , Furong Huang

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Tong Chen , Zhan Ma

Federated learning (FL) enables collaborative model training through model parameter exchanges instead of raw data. To avoid potential inference attacks from exchanged parameters, differential privacy (DP) offers rigorous guarantee against…

Cryptography and Security · Computer Science 2025-01-14 Shu Hong , Xiaojun Lin , Lingjie Duan

As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(\epsilon, \delta)$-differential privacy, while prevalent, exhibits limited adaptability for many applications.…

Cryptography and Security · Computer Science 2025-07-03 Yifeng Liu , Zehua Wang

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input…

Machine Learning · Computer Science 2018-07-10 Xiaoyong Yuan , Pan He , Qile Zhu , Xiaolin Li

Many defenses against adversarial attacks (\eg robust classifiers, randomization, or image purification) use countermeasures put to work only after the attack has been crafted. We adopt a different perspective to introduce $A^5$…

Machine Learning · Computer Science 2023-05-24 Iuri Frosio , Jan Kautz

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Computation and Language · Computer Science 2021-10-18 Wenkai Yang , Yankai Lin , Peng Li , Jie Zhou , Xu Sun

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Machine Learning · Computer Science 2021-04-26 Jonathan Hayase , Weihao Kong , Raghav Somani , Sewoong Oh

Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we…

Machine Learning · Computer Science 2021-01-11 Alexander Levine , Soheil Feizi

Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

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

Adversarial robustness research primarily focuses on L_p perturbations, and most defenses are developed with identical training-time and test-time adversaries. However, in real-world applications developers are unlikely to have access to…