English
Related papers

Related papers: The Curious Case of Adversarially Robust Models: M…

200 papers

This paper mathematically derives an analytic solution of the adversarial perturbation on a ReLU network, and theoretically explains the difficulty of adversarial training. Specifically, we formulate the dynamics of the adversarial…

Machine Learning · Computer Science 2022-05-31 Xu Cheng , Hao Zhang , Yue Xin , Wen Shen , Jie Ren , Quanshi Zhang

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN),…

Cryptography and Security · Computer Science 2019-01-04 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

We study the robustness of machine learning approaches to adversarial perturbations, with a focus on supervised learning scenarios. We find that typical phase classifiers based on deep neural networks are extremely vulnerable to adversarial…

Disordered Systems and Neural Networks · Physics 2024-01-26 Si Jiang , Sirui Lu , Dong-Ling Deng

As deep learning (DL) models are increasingly being integrated into our everyday lives, ensuring their safety by making them robust against adversarial attacks has become increasingly critical. DL models have been found to be susceptible to…

Machine Learning · Computer Science 2026-05-29 Hallgrimur Thorsteinsson , Valdemar J Henriksen , Daniel I R Cruz , Raghavendra Selvan , Tong Chen

Training adversarially robust discriminative (i.e., softmax) classifier has been the dominant approach to robust classification. Building on recent work on adversarial training (AT)-based generative models, we investigate using AT to learn…

Machine Learning · Computer Science 2022-12-15 Xuwang Yin

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…

Machine Learning · Computer Science 2020-09-11 Theodoros Tsiligkaridis , Jay Roberts

It is well-known that the performance of well-trained deep neural networks may degrade significantly when they are applied to data with even slightly shifted distributions. Recent studies have shown that introducing certain perturbation on…

Computer Vision and Pattern Recognition · Computer Science 2023-01-31 Yabin Zhang , Bin Deng , Ruihuang Li , Kui Jia , Lei Zhang

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…

Machine Learning · Computer Science 2023-06-13 Piersilvio De Bartolomeis , Jacob Clarysse , Amartya Sanyal , Fanny Yang

Adversarial data augmentation has shown promise for training robust deep neural networks against unforeseen data shifts or corruptions. However, it is difficult to define heuristics to generate effective fictitious target distributions…

Machine Learning · Computer Science 2020-12-21 Long Zhao , Ting Liu , Xi Peng , Dimitris Metaxas

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

This work investigates adversarial training in the context of margin-based linear classifiers in the high-dimensional regime where the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha = n / d$. We introduce…

Machine Learning · Statistics 2026-01-13 Kasimir Tanner , Matteo Vilucchio , Bruno Loureiro , Florent Krzakala

Adversarial training augments the training set with perturbations to improve the robust error (over worst-case perturbations), but it often leads to an increase in the standard error (on unperturbed test inputs). Previous explanations for…

Machine Learning · Computer Science 2020-07-08 Aditi Raghunathan , Sang Michael Xie , Fanny Yang , John Duchi , Percy Liang

The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). Despite many previous works studying the reason behind such adversarial behavior, the relationship between the…

Machine Learning · Statistics 2019-06-07 Yujun Shi , Benben Liao , Guangyong Chen , Yun Liu , Ming-Ming Cheng , Jiashi Feng

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…

Machine Learning · Computer Science 2022-10-05 Chaojian Yu , Dawei Zhou , Li Shen , Jun Yu , Bo Han , Mingming Gong , Nannan Wang , Tongliang Liu

Prior studies have unveiled the vulnerability of the deep neural networks in the context of adversarial machine learning, leading to great recent attention into this area. One interesting question that has yet to be fully explored is the…

Machine Learning · Computer Science 2020-08-04 Hossein Aboutalebi , Mohammad Javad Shafiee , Michelle Karg , Christian Scharfenberger , Alexander Wong

Neural models often exploit superficial features to achieve good performance, rather than deriving more general features. Overcoming this tendency is a central challenge in areas such as representation learning and ML fairness. Recent work…

Computation and Language · Computer Science 2020-10-12 Rohan Jha , Charles Lovering , Ellie Pavlick

Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 João Monteiro , Isabela Albuquerque , Zahid Akhtar , Tiago H. Falk

Deep learning models frequently suffer from various problems such as class imbalance and lack of robustness to distribution shift. It is often difficult to find data suitable for training beyond the available benchmarks. This is especially…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Pratinav Seth , Akshat Bhandari , Kumud Lakara

A necessary characteristic for the deployment of deep learning models in real world applications is resistance to small adversarial perturbations while maintaining accuracy on non-malicious inputs. While robust training provides models that…

Machine Learning · Statistics 2020-02-27 Aditya Saligrama , Guillaume Leclerc