English
Related papers

Related papers: Denoised Smoothing: A Provable Defense for Pretrai…

200 papers

Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…

Machine Learning · Computer Science 2023-05-09 Ambar Pal , Jeremias Sulam

Randomized smoothing, a method to certify a classifier's decision on an input is invariant under adversarial noise, offers attractive advantages over other certification methods. It operates in a black-box and so certification is not…

Machine Learning · Computer Science 2020-06-09 Jamie Hayes

Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that this property can be utilized for designing classifiers…

Machine Learning · Computer Science 2024-05-24 Ambar Pal , René Vidal , Jeremias Sulam

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 present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to…

Cryptography and Security · Computer Science 2025-06-03 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Image denoising can remove natural noise that widely exists in images captured by multimedia devices due to low-quality imaging sensors, unstable image transmission processes, or low light conditions. Recent works also find that image…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Yupeng Cheng , Qing Guo , Felix Juefei-Xu , Wei Feng , Shang-Wei Lin , Weisi Lin , Yang Liu

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…

Machine Learning · Computer Science 2020-12-24 Aishan Liu , Xianglong Liu , Chongzhi Zhang , Hang Yu , Qiang Liu , Dacheng Tao

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning…

Computer Vision and Pattern Recognition · Computer Science 2021-10-06 Xiaoyu Lin , Deblina Bhattacharjee , Majed El Helou , Sabine Süsstrunk

While adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attacked images into clean images with a standalone purification model, has…

Machine Learning · Computer Science 2021-06-14 Jongmin Yoon , Sung Ju Hwang , Juho Lee

Recent studies have demonstrated that machine learning approaches like deep neural networks (DNNs) are easily fooled by adversarial attacks. Subtle and imperceptible perturbations of the data are able to change the result of deep neural…

Machine Learning · Computer Science 2020-02-25 Negin Entezari , Evangelos E. Papalexakis

With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification. A potential concern is the so-called "fair-washing" -…

Machine Learning · Computer Science 2020-07-14 Laura Rieger , Lars Kai Hansen

Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these…

Machine Learning · Computer Science 2020-10-26 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Randomized smoothing is the state-of-the-art approach to construct image classifiers that are provably robust against additive adversarial perturbations of bounded magnitude. However, it is more complicated to construct reasonable…

Computer Vision and Pattern Recognition · Computer Science 2024-08-12 Dmitrii Korzh , Mikhail Pautov , Olga Tsymboi , Ivan Oseledets

While deep neural networks have proven to be a powerful tool for many recognition and classification tasks, their stability properties are still not well understood. In the past, image classifiers have been shown to be vulnerable to…

Computer Vision and Pattern Recognition · Computer Science 2019-01-14 Rima Alaifari , Giovanni S. Alberti , Tandri Gauksson

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen types of adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Dawei Zhou , Tongliang Liu , Bo Han , Nannan Wang , Chunlei Peng , Xinbo Gao

In this paper we provide an approach for deep learning that protects against adversarial examples in image classification-type networks. The approach relies on two mechanisms:1) a mechanism that increases robustness at the expense of…

Machine Learning · Computer Science 2021-01-07 Yuting Liang , Reza Samavi

We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or…

Machine Learning · Statistics 2021-04-30 Thomas Brunner , Frederik Diehl , Michael Truong Le , Alois Knoll

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine Learning · Computer Science 2019-11-12 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

Adversarial training is one of the strongest defenses against adversarial attacks, but it requires adversarial examples to be generated for every mini-batch during optimization. The expense of producing these examples during training often…

Machine Learning · Computer Science 2019-10-28 Ali Shafahi , Amin Ghiasi , Furong Huang , Tom Goldstein

Adversarial attacks that generate small L_p-norm perturbations to mislead classifiers have limited success in black-box settings and with unseen classifiers. These attacks are also not robust to defenses that use denoising filters and to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Ali Shahin Shamsabadi , Ricardo Sanchez-Matilla , Andrea Cavallaro