English
Related papers

Related papers: Gradient Obfuscation Checklist Test Gives a False …

200 papers

Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarantee provisions. Now, the objective is to not only mislead a…

Machine Learning · Computer Science 2025-11-19 Quoc Viet Vo , Tashreque M. Haq , Paul Montague , Tamas Abraham , Ehsan Abbasnejad , Damith C. Ranasinghe

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

Machine Learning · Computer Science 2021-06-10 Boxi Wu , Heng Pan , Li Shen , Jindong Gu , Shuai Zhao , Zhifeng Li , Deng Cai , Xiaofei He , Wei Liu

Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy…

Machine Learning · Computer Science 2021-06-30 Oliver Bryniarski , Nabeel Hingun , Pedro Pachuca , Vincent Wang , Nicholas Carlini

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Machine Learning · Computer Science 2020-04-28 Jan Philip Göpfert , André Artelt , Heiko Wersing , Barbara Hammer

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…

Machine Learning · Computer Science 2018-06-13 Jonathan Uesato , Brendan O'Donoghue , Aaron van den Oord , Pushmeet Kohli

This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive…

Cryptography and Security · Computer Science 2024-11-01 Steve Bakos , Pooria Madani , Heidar Davoudi

We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Alessandro Cappelli , Ruben Ohana , Julien Launay , Laurent Meunier , Iacopo Poli , Florent Krzakala

As a defense strategy against adversarial attacks, adversarial detection aims to identify and filter out adversarial data from the data flow based on discrepancies in distribution and noise patterns between natural and adversarial data.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Qian Wang , Chen Li , Yuchen Luo , Hefei Ling , Shijuan Huang , Ruoxi Jia , Ning Yu

While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input,…

Machine Learning · Computer Science 2019-06-11 Cecilia Summers , Michael J. Dinneen

Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood, theoretical…

Machine Learning · Computer Science 2020-12-01 George Cazenavette , Calvin Murdock , Simon Lucey

Adversarial attacks and defenses are currently active areas of research for the deep learning community. A recent review paper divided the defense approaches into three categories; gradient masking, robust optimization, and adversarial…

Machine Learning · Computer Science 2019-10-24 Leslie N. Smith

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Yuhang Wu , Sunpreet S. Arora , Yanhong Wu , Hao Yang

Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…

Machine Learning · Computer Science 2024-09-13 Oliver J. Sutton , Qinghua Zhou , Ivan Y. Tyukin , Alexander N. Gorban , Alexander Bastounis , Desmond J. Higham

The vulnerability of machine learning models to adversarial attacks remains a critical security challenge. Traditional defenses, such as adversarial training, typically robustify models by minimizing a worst-case loss. However, these…

Machine Learning · Statistics 2025-10-13 Pablo G. Arce , Roi Naveiro , David Ríos Insua

Robust classification is essential in tasks like autonomous vehicle sign recognition, where the downsides of misclassification can be grave. Adversarial attacks threaten the robustness of neural network classifiers, causing them to…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Andrew Wang , Wyatt Mayor , Ryan Smith , Gopal Nookula , Gregory Ditzler

Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images can be slightly…

Machine Learning · Computer Science 2021-03-04 Jacob Abernethy , Pranjal Awasthi , Satyen Kale

A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs). Yet, the standard methodology has a serious flaw - virtually all of the defenses…

Machine Learning · Computer Science 2023-02-01 Felix Mujkanovic , Simon Geisler , Stephan Günnemann , Aleksandar Bojchevski

Recent work has put forth the hypothesis that adversarial vulnerabilities in neural networks are due to them overusing "non-robust features" inherent in the training data. We show empirically that for PGD-attacks, there is a training stage…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Zuowen Wang , Leo Horne

Gradient-based adversarial attacks on neural networks can be crafted in a variety of ways by varying either how the attack algorithm relies on the gradient, the network architecture used for crafting the attack, or both. Most recent work…

Machine Learning · Computer Science 2020-01-28 Rehana Mahfuz , Rajeev Sahay , Aly El Gamal

Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks. However, the robust accuracy of present state-ofthe-art defenses is far from the requirements in critical applications such as…

Machine Learning · Computer Science 2023-06-13 Sravanti Addepalli , Samyak Jain , Gaurang Sriramanan , R. Venkatesh Babu