English
Related papers

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

200 papers

Certified defense using randomized smoothing is a popular technique to provide robustness guarantees for deep neural networks against l2 adversarial attacks. Existing works use this technique to provably secure a pretrained non-robust model…

Machine Learning · Computer Science 2022-10-18 Gaurav Kumar Nayak , Ruchit Rawal , Anirban Chakraborty

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…

Machine Learning · Computer Science 2020-01-13 Hadi Salman , Greg Yang , Jerry Li , Pengchuan Zhang , Huan Zhang , Ilya Razenshteyn , Sebastien Bubeck

We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique has been proposed…

Machine Learning · Computer Science 2019-06-18 Jeremy M Cohen , Elan Rosenfeld , J. Zico Kolter

Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images. To defend against adversarial attacks in a training-free and attack-agnostic manner, this…

Computer Vision and Pattern Recognition · Computer Science 2021-08-03 Li Ding , Yongwei Wang , Xin Ding , Kaiwen Yuan , Ping Wang , Hua Huang , Z. Jane Wang

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

Recent advancements in masked image modeling (MIM) have made it a prevailing framework for self-supervised visual representation learning. The MIM pretrained models, like most deep neural network methods, remain vulnerable to adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Zunzhi You , Daochang Liu , Bohyung Han , Chang Xu

Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Tao Bai , Jun Zhao , Lanqing Guo , Bihan Wen

We propose a novel and effective purification based adversarial defense method against pre-processor blind white- and black-box attacks. Our method is computationally efficient and trained only with self-supervised learning on general…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Sungmin Cha , Naeun Ko , Youngjoon Yoo , Taesup Moon

Adversarial perturbations can be added to images to protect their content from unwanted inferences. These perturbations may, however, be ineffective against classifiers that were not {seen} during the generation of the perturbation, or…

Computer Vision and Pattern Recognition · Computer Science 2020-10-01 Ricardo Sanchez-Matilla , Chau Yi Li , Ali Shahin Shamsabadi , Riccardo Mazzon , Andrea Cavallaro

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has…

Machine Learning · Computer Science 2024-06-21 Harrison Gietz , Jugal Kalita

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

To deflect adversarial attacks, a range of "certified" classifiers have been proposed. In addition to labeling an image, certified classifiers produce (when possible) a certificate guaranteeing that the input image is not an…

Machine Learning · Computer Science 2020-03-20 Amin Ghiasi , Ali Shafahi , Tom Goldstein

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Computation and Language · Computer Science 2025-05-20 Zhenhao Li , Huichi Zhou , Marek Rei , Lucia Specia

Randomized smoothing is a well-established method for achieving certified robustness against l2-adversarial perturbations. By incorporating a denoiser before the base classifier, pretrained classifiers can be seamlessly integrated into…

Machine Learning · Computer Science 2025-09-16 Ali Hedayatnia , Mostafa Tavassolipour , Babak Nadjar Araabi , Abdol-Hossein Vahabie

Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each…

Machine Learning · Computer Science 2019-03-27 Yuchen Zhang , Percy Liang

Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to certify the robustness of semantic segmentation models against…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Maksym Yatsura , Kaspar Sakmann , N. Grace Hua , Matthias Hein , Jan Hendrik Metzen

In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To do so, we instantiate the denoised smoothing approach of…

Machine Learning · Computer Science 2023-03-07 Nicholas Carlini , Florian Tramer , Krishnamurthy Dj Dvijotham , Leslie Rice , Mingjie Sun , J. Zico Kolter

Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models…

Computation and Language · Computer Science 2024-04-19 Jiabao Ji , Bairu Hou , Zhen Zhang , Guanhua Zhang , Wenqi Fan , Qing Li , Yang Zhang , Gaowen Liu , Sijia Liu , Shiyu Chang

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

Machine Learning · Computer Science 2019-11-28 Chao Tang , Yifei Fan , Anthony Yezzi

We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial examples, while adapting to the input. Our key insight is to reinterpret a guided denoising diffusion model as a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Frederick Shpilevskiy , Saiyue Lyu , Krishnamurthy Dj Dvijotham , Mathias Lécuyer , Pierre-André Noël
‹ Prev 1 2 3 10 Next ›