English
Related papers

Related papers: (De)Randomized Smoothing for Certifiable Defense a…

200 papers

Adversarial attacks expose a fundamental vulnerability in modern deep vision models by exploiting their dependence on dense, pixel-level representations that are highly sensitive to imperceptible perturbations. Traditional defense…

Computer Vision and Pattern Recognition · Computer Science 2025-11-13 Jingjie He , Weijie Liang , Zihan Shan , Matthew Caesar

Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can achieve strong robustness in practice, but lack formal guarantees, motivating the need for…

Machine Learning · Computer Science 2026-05-26 Konstantinos Emmanouilidis , Tianjiao Ding , Nghia Nguyen , Nicolas Loizou , René Vidal

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

Adversarial patches present significant challenges to the robustness of deep learning models, making the development of effective defenses become critical for real-world applications. This paper introduces DIFFender, a novel DIFfusion-based…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Xingxing Wei , Caixin Kang , Yinpeng Dong , Zhengyi Wang , Shouwei Ruan , Yubo Chen , Hang Su

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

Neural Networks are infamously sensitive to small perturbations in their inputs, making them vulnerable to adversarial attacks. This project evaluates the performance of Denoising Diffusion Probabilistic Models (DDPM) as a purification…

Machine Learning · Computer Science 2023-01-18 Lars Lien Ankile , Anna Midgley , Sebastian Weisshaar

In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the…

Machine Learning · Computer Science 2024-06-13 Andrew C. Cullen , Shijie Liu , Paul Montague , Sarah M. Erfani , Benjamin I. P. Rubinstein

In the literature on adversarial examples, white box and black box attacks have received the most attention. The adversary is assumed to have either full (white) or no (black) access to the defender's model. In this work, we focus on the…

Machine Learning · Computer Science 2022-03-22 Shi Hu , Eric Nalisnick , Max Welling

Randomized smoothing is currently the state-of-the-art method that provides certified robustness for deep neural networks. However, due to its excessively conservative nature, this method of incomplete verification often cannot achieve an…

Machine Learning · Computer Science 2023-12-29 Bo-Han Kung , Shang-Tse Chen

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

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

Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-04 Zhaoyu Chen , Bo Li , Shuang Wu , Shouhong Ding , Wenqiang Zhang

The widespread deployment of pre-trained language models (PLMs) has exposed them to textual backdoor attacks, particularly those planted during the pre-training stage. These attacks pose significant risks to high-reliability applications,…

Machine Learning · Computer Science 2025-02-12 Bowei He , Lihao Yin , Hui-Ling Zhen , Jianping Zhang , Lanqing Hong , Mingxuan Yuan , Chen Ma

Image segmentation is an important problem in many safety-critical applications. Recent studies show that modern image segmentation models are vulnerable to adversarial perturbations, while existing attack methods mainly follow the idea of…

Computer Vision and Pattern Recognition · Computer Science 2023-04-07 Wenjie Qu , Youqi Li , Binghui Wang

Physical adversarial attacks on deep learning systems is concerning due to the ease of deploying such attacks, usually by placing an adversarial patch in a scene to manipulate the outcomes of a deep learning model. Training such patches…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Harrison Bagley , Will Meakin , Simon Lucey , Yee Wei Law , Tat-Jun Chin

Deep Learning models are highly susceptible to adversarial manipulations that can lead to catastrophic consequences. One of the most effective methods to defend against such disturbances is adversarial training but at the cost of…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Samuel Henrique Silva , Arun Das , Ian Scarff , Peyman Najafirad

Certified robustness guarantee gauges a model's robustness to test-time attacks and can assess the model's readiness for deployment in the real world. In this work, we critically examine how the adversarial robustness guarantees from…

Machine Learning · Computer Science 2021-12-02 Jiachen Sun , Akshay Mehra , Bhavya Kailkhura , Pin-Yu Chen , Dan Hendrycks , Jihun Hamm , Z. Morley Mao

While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This…

Machine Learning · Computer Science 2024-07-23 Yatong Bai , Brendon G. Anderson , Aerin Kim , Somayeh Sojoudi

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

Adversarial patch attacks threaten the reliability of modern vision models. We present PatchMap, the first spatially exhaustive benchmark of patch placement, built by evaluating over 1.5e8 forward passes on ImageNet validation images.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Shai Kimhi , Avi Mendlson , Moshe Kimhi