English
Related papers

Related papers: Non-Robust Features are Not Always Useful in One-C…

200 papers

Despite the great success achieved in machine learning (ML), adversarial examples have caused concerns with regards to its trustworthiness: A small perturbation of an input results in an arbitrary failure of an otherwise seemingly…

Machine Learning · Computer Science 2018-10-24 Jingkang Wang , Ruoxi Jia , Gerald Friedland , Bo Li , Costas Spanos

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Levente Halmosi , Bálint Mohos , Márk Jelasity

In this paper, we address the open question: "What do adversarially robust models look at?" Recently, it has been reported in many works that there exists the trade-off between standard accuracy and adversarial robustness. According to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Takahiro Itazuri , Yoshihiro Fukuhara , Hirokatsu Kataoka , Shigeo Morishima

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

Machine Learning · Computer Science 2021-05-26 Leo Schwinn , René Raab , An Nguyen , Dario Zanca , Bjoern Eskofier

In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy. However, the other…

Machine Learning · Computer Science 2021-06-01 Jingfeng Zhang , Jianing Zhu , Gang Niu , Bo Han , Masashi Sugiyama , Mohan Kankanhalli

Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning…

Computer Vision and Pattern Recognition · Computer Science 2022-03-18 Mattia Carletti , Matteo Terzi , Gian Antonio Susto

Adversarial examples pose a unique challenge for deep learning systems. Despite recent advances in both attacks and defenses, there is still a lack of clarity and consensus in the community about the true nature and underlying properties of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Shishira R Maiya , Max Ehrlich , Vatsal Agarwal , Ser-Nam Lim , Tom Goldstein , Abhinav Shrivastava

Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well insights about the…

Cryptography and Security · Computer Science 2019-11-19 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes

Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standard machine learning models are not robust. This suggests that…

Machine Learning · Statistics 2018-11-28 Suproteem K. Sarkar , Kojin Oshiba , Daniel Giebisch , Yaron Singer

Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Alexey Kurakin , Ian Goodfellow , Samy Bengio

Adversarial examples have appeared as a ubiquitous property of machine learning models where bounded adversarial perturbation could mislead the models to make arbitrarily incorrect predictions. Such examples provide a way to assess the…

Machine Learning · Computer Science 2021-03-02 Zhuolin Yang , Zhaoxi Chen , Tiffany Cai , Xinyun Chen , Bo Li , Yuandong Tian

A wide range of defenses have been proposed to harden neural networks against adversarial attacks. However, a pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at…

Machine Learning · Computer Science 2020-02-05 Ali Shafahi , W. Ronny Huang , Christoph Studer , Soheil Feizi , Tom Goldstein

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…

Machine Learning · Statistics 2022-07-05 Elvis Dohmatob , Alberto Bietti

Machine learning (ML) models are often sensitive to carefully crafted yet seemingly unnoticeable perturbations. Such adversarial examples are considered to be a property of ML models, often associated with their black-box operation and…

Machine Learning · Computer Science 2025-04-29 Elad Sofer , Tomer Shaked , Caroline Chaux , Nir Shlezinger

Adversarial robustness studies the worst-case performance of a machine learning model to ensure safety and reliability. With the proliferation of deep-learning-based technology, the potential risks associated with model development and…

Machine Learning · Computer Science 2023-01-06 Pin-Yu Chen , Sijia Liu

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…

We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks can improve upon adversarial training. Our evaluation under a…

Machine Learning · Computer Science 2021-07-14 Iryna Korshunova , David Stutz , Alexander A. Alemi , Olivia Wiles , Sven Gowal

Adversarial training (AT) has been considered one of the most effective methods for making deep neural networks robust against adversarial attacks, while the training mechanisms and dynamics of AT remain open research problems. In this…

Machine Learning · Computer Science 2025-06-06 Zeming Wei , Yiwen Guo , Yisen Wang

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

Machine Learning · Computer Science 2022-06-17 Florian Tramèr

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Hadi Salman , Andrew Ilyas , Logan Engstrom , Ashish Kapoor , Aleksander Madry