English
Related papers

Related papers: Extensions and limitations of randomized smoothing…

200 papers

Recent studies have shown that regularization techniques using soft labels, e.g., label smoothing, Mixup, and CutMix, not only enhance image classification accuracy but also mitigate miscalibration due to overconfident predictions, and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-17 Jonghyun Park , Juyeop Kim , Jong-Seok Lee

This paper presents novel methods for estimating certified radii in randomized smoothing, a technique crucial for certifying the robustness of neural networks against adversarial perturbations. Our proposed techniques significantly improve…

Machine Learning · Computer Science 2025-03-13 Zixuan Liang

Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed as an alternative to deterministic ones. However,…

Machine Learning · Computer Science 2023-11-29 Lucas Gnecco-Heredia , Yann Chevaleyre , Benjamin Negrevergne , Laurent Meunier , Muni Sreenivas Pydi

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…

Machine Learning · Computer Science 2024-05-28 Jieren Deng , Hanbin Hong , Aaron Palmer , Xin Zhou , Jinbo Bi , Kaleel Mahmood , Yuan Hong , Derek Aguiar

We give a formal verification procedure that decides whether a classifier ensemble is robust against arbitrary randomized attacks. Such attacks consist of a set of deterministic attacks and a distribution over this set. The…

Machine Learning · Computer Science 2020-07-10 Dennis Gross , Nils Jansen , Guillermo A. Pérez , Stephan Raaijmakers

In most practical problems of classifier learning, the training data suffers from the label noise. Hence, it is important to understand how robust is a learning algorithm to such label noise. This paper presents some theoretical analysis to…

Machine Learning · Computer Science 2016-08-29 Aritra Ghosh , Naresh Manwani , P. S. Sastry

Certified defenses such as randomized smoothing have shown promise towards building reliable machine learning systems against $\ell_p$-norm bounded attacks. However, existing methods are insufficient or unable to provably defend against…

Machine Learning · Computer Science 2022-06-30 Zhongkai Hao , Chengyang Ying , Yinpeng Dong , Hang Su , Jun Zhu , Jian Song

Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g., adversarial training. Randomized smoothing, the averaging of…

Tree-based models are used in many high-stakes application domains such as finance and medicine, where robustness and interpretability are of utmost importance. Yet, methods for improving and certifying their robustness are severely…

Machine Learning · Computer Science 2022-11-16 Miklós Z. Horváth , Mark Niklas Müller , Marc Fischer , Martin Vechev

Randomized smoothing has achieved state-of-the-art certified robustness against $l_2$-norm adversarial attacks. However, it is not wholly resolved on how to find the optimal base classifier for randomized smoothing. In this work, we employ…

Machine Learning · Computer Science 2021-02-24 Chizhou Liu , Yunzhen Feng , Ranran Wang , Bin Dong

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

Machine Learning · Computer Science 2023-09-06 Ruihan Zhang , Peixin Zhang , Jun Sun

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…

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

As reinforcement learning (RL) has achieved great success and been even adopted in safety-critical domains such as autonomous vehicles, a range of empirical studies have been conducted to improve its robustness against adversarial attacks.…

Machine Learning · Computer Science 2022-03-17 Fan Wu , Linyi Li , Zijian Huang , Yevgeniy Vorobeychik , Ding Zhao , Bo Li

A machine learning model is traditionally considered robust if its prediction remains (almost) constant under input perturbations with small norm. However, real-world tasks like molecular property prediction or point cloud segmentation have…

Machine Learning · Computer Science 2024-01-17 Jan Schuchardt , Yan Scholten , Stephan Günnemann

In this paper we criticize the robustness measure traditionally employed to assess the performance of machine learning models deployed in adversarial settings. To mitigate the limitations of robustness, we introduce a new measure called…

Machine Learning · Computer Science 2021-12-07 Stefano Calzavara , Lorenzo Cazzaro , Claudio Lucchese , Federico Marcuzzi , Salvatore Orlando

Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the…

Machine Learning · Computer Science 2025-06-19 Alaa Anani , Tobias Lorenz , Mario Fritz , Bernt Schiele

Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable robustness to adversarial examples: a) explicitly training…

Machine Learning · Computer Science 2025-08-04 Meiyu Zhong , Ravi Tandon

We propose a novel deterministic purification method to improve adversarial robustness by mapping a potentially adversarial sample toward a nearby sample that lies close to a mode of the data distribution, where classifiers are more…

Machine Learning · Computer Science 2026-02-09 Vinh Hoang , Sebastian Krumscheid , Holger Rauhut , Raúl Tempone
‹ Prev 1 4 5 6 7 8 10 Next ›