English
Related papers

Related papers: Robustness May Be at Odds with Accuracy

200 papers

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…

Machine Learning · Computer Science 2019-10-21 Florian Tramèr , Dan Boneh

Historically, machine learning methods have not been designed with security in mind. In turn, this has given rise to adversarial examples, carefully perturbed input samples aimed to mislead detection at test time, which have been applied to…

Machine Learning · Computer Science 2022-01-11 Jamie Hayes

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Machine Learning · Computer Science 2020-08-13 Alex Serban , Erik Poll , Joost Visser

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Fatemeh Amerehi , Patrick Healy

Adversarial training tends to result in models that are less accurate on natural (unperturbed) examples compared to standard models. This can be attributed to either an algorithmic shortcoming or a fundamental property of the training data…

Machine Learning · Computer Science 2021-07-02 Alireza Mousavi Hosseini , Amir Mohammad Abouei , Mohammad Hossein Rohban

In the last a few decades, deep neural networks have achieved remarkable success in machine learning, computer vision, and pattern recognition. Recent studies however show that neural networks (both shallow and deep) may be easily fooled by…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Zhuang Qian , Kaizhu Huang , Qiu-Feng Wang , Xu-Yao Zhang

An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing…

Machine Learning · Statistics 2019-09-30 Logan Engstrom , Andrew Ilyas , Shibani Santurkar , Dimitris Tsipras , Brandon Tran , Aleksander Madry

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different prediction. Conversely, obstinate adversarial examples occur…

Computation and Language · Computer Science 2022-11-01 Hannah Chen , Yangfeng Ji , David Evans

Adversarial examples mainly exploit changes to input pixels to which humans are not sensitive to, and arise from the fact that models make decisions based on uninterpretable features. Interestingly, cognitive science reports that the…

In this paper, for the first time, we propose an evaluation method for deep learning models that assesses the performance of a model not only in an unseen test scenario, but also in extreme cases of noise, outliers and ambiguous input data.…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Magdalini Paschali , Sailesh Conjeti , Fernando Navarro , Nassir Navab

Adversarial examples are carefully perturbed in-puts for fooling machine learning models. A well-acknowledged defense method against such examples is adversarial training, where adversarial examples are injected into training data to…

Machine Learning · Computer Science 2019-05-17 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

We demonstrate that the choice of optimizer, neural network architecture, and regularizer significantly affect the adversarial robustness of linear neural networks, providing guarantees without the need for adversarial training. To this…

Machine Learning · Computer Science 2021-06-08 Fartash Faghri , Sven Gowal , Cristina Vasconcelos , David J. Fleet , Fabian Pedregosa , Nicolas Le Roux

While the traditional formulation of machine learning tasks is in terms of performance on average, in practice we are often interested in how well a trained model performs on rare or difficult data points at test time. To achieve more…

Machine Learning · Computer Science 2025-12-29 Matthew J. Holland , Toma Hamada

Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothing. Under the…

Machine Learning · Computer Science 2022-12-21 Jongheon Jeong , Seojin Kim , Jinwoo Shin

To ensure trust in AI models, it is becoming increasingly apparent that evaluation of models must be extended beyond traditional performance metrics, like accuracy, to other dimensions, such as fairness, explainability, adversarial…

Machine Learning · Computer Science 2021-10-01 Moninder Singh , Gevorg Ghalachyan , Kush R. Varshney , Reginald E. Bryant

Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples…

Machine Learning · Computer Science 2019-10-10 Alfred Laugros , Alice Caplier , Matthieu Ospici

Adversarial training has shown its ability in producing models that are robust to perturbations on the input data, but usually at the expense of decrease in the standard accuracy. To mitigate this issue, it is commonly believed that more…

Machine Learning · Computer Science 2020-06-09 Yifei Min , Lin Chen , Amin Karbasi

Quantifying robustness in a single measure for the purposes of model selection, development of adversarial training methods, and anticipating trends has so far been elusive. The simplest metric to consider is the number of trainable…

Machine Learning · Computer Science 2024-10-25 David Khachaturov , Robert Mullins

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

State-of-the-art classifiers have been shown to be largely vulnerable to adversarial perturbations. One of the most effective strategies to improve robustness is adversarial training. In this paper, we investigate the effect of adversarial…

Machine Learning · Computer Science 2018-11-27 Seyed-Mohsen Moosavi-Dezfooli , Alhussein Fawzi , Jonathan Uesato , Pascal Frossard
‹ Prev 1 4 5 6 7 8 10 Next ›