English
Related papers

Related papers: When Flatness Does (Not) Guarantee Adversarial Rob…

200 papers

Convolutional neural networks are currently the state-of-the-art algorithms for many remote sensing applications such as semantic segmentation or object detection. However, these algorithms are extremely sensitive to over-fitting, domain…

Computer Vision and Pattern Recognition · Computer Science 2021-05-31 Adrien Chan-Hon-Tong , Gaston Lenczner , Aurelien Plyer

Adversarial robustness, which primarily comprises sensitivity-based robustness and spatial robustness, plays an integral part in achieving robust generalization. In this paper, we endeavor to design strategies to achieve universal…

Machine Learning · Computer Science 2024-06-25 Ke Sun , Mingjie Li , Zhouchen Lin

Over the past decade, numerous theories have been proposed to explain the widespread vulnerability of deep neural networks to adversarial evasion attacks. Among these, the theory of non-robust features proposed by Ilyas et al. has been…

Machine Learning · Computer Science 2026-01-05 Jennifer Crawford , Amol Khanna , Fred Lu , Amy R. Wagoner , Stella Biderman , Andre T. Nguyen , Edward Raff

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness of neural networks…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Sadaf Gulshad , Jan Hendrik Metzen , Arnold Smeulders

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the…

Machine Learning · Computer Science 2023-05-03 Lukas Gosch , Daniel Sturm , Simon Geisler , Stephan Günnemann

Carefully crafted, often imperceptible, adversarial perturbations have been shown to cause state-of-the-art models to yield extremely inaccurate outputs, rendering them unsuitable for safety-critical application domains. In addition, recent…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Yash Sharma , Gavin Weiguang Ding , Marcus Brubaker

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision…

Computer Vision and Pattern Recognition · Computer Science 2017-05-29 Alhussein Fawzi , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard , Stefano Soatto

In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness. For this purpose, we selectively retrain different portions of VGG and…

Machine Learning · Computer Science 2021-11-01 Shoaib Ahmed Siddiqui , Thomas Breuel

It is well known that artificial neural networks are vulnerable to adversarial examples, in which great efforts have been made to improve the robustness. However, such examples are usually imperceptible to humans, and thus their effect on…

Neural and Evolutionary Computing · Computer Science 2021-06-29 Liu Yuezhang , Bo Li , Qifeng Chen

Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the…

Machine Learning · Computer Science 2023-11-28 Svetlana Pavlitska , Hannes Grolig , J. Marius Zöllner

This work attempts to address adversarial robustness of deep networks by means of novel learning arguments. Specifically, inspired from results in neuroscience, we propose a local competition principle as a means of adversarially-robust…

Machine Learning · Computer Science 2020-06-19 Antonios Alexos , Konstantinos P. Panousis , Sotirios Chatzis

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

Machine Learning · Computer Science 2021-07-27 Ali Rahmati , Seyed-Mohsen Moosavi-Dezfooli , Huaiyu Dai

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions,…

Machine Learning · Computer Science 2021-12-15 Yao Qin , Xuezhi Wang , Alex Beutel , Ed H. Chi

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Machine Learning · Computer Science 2019-02-25 Gavin Weiguang Ding , Kry Yik Chau Lui , Xiaomeng Jin , Luyu Wang , Ruitong Huang

Over the past few years, several adversarial training methods have been proposed to improve the robustness of machine learning models against adversarial perturbations in the input. Despite remarkable progress in this regard, adversarial…

Machine Learning · Computer Science 2022-04-04 Adel Javanmard , Mohammad Mehrabi

Neural networks have been proven to be both highly effective within computer vision, and highly vulnerable to adversarial attacks. Consequently, as the use of neural networks increases due to their unrivaled performance, so too does the…

Machine Learning · Computer Science 2023-04-03 Timothy Redgrave , Colton Crum

Adversarial examples are often cited by neuroscientists and machine learning researchers as an example of how computational models diverge from biological sensory systems. Recent work has proposed adding biologically-inspired components to…

Neurons and Cognition · Quantitative Biology 2021-11-16 Joel Dapello , Jenelle Feather , Hang Le , Tiago Marques , David D. Cox , Josh H. McDermott , James J. DiCarlo , SueYeon Chung

The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014). We provide a theoretical framework for analyzing the…

Machine Learning · Computer Science 2016-03-30 Alhussein Fawzi , Omar Fawzi , Pascal Frossard

Deep neural networks are known to be vulnerable to adversarial perturbations, which are small and carefully crafted inputs that lead to incorrect predictions. In this paper, we propose DeepDefense, a novel defense framework that applies…

Machine Learning · Computer Science 2025-11-19 Ci Lin , Tet Yeap , Iluju Kiringa , Biwei Zhang

Adversarial attacks in the form of imperceptible perturbations of normal images have been extensively studied, and for every new defense methodology created, multiple adversarial attacks are found to counteract it. In particular, a popular…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Carl Cheng , Evan Hu