English
Related papers

Related papers: Depth-2 Neural Networks Under a Data-Poisoning Att…

200 papers

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

We develop a fast end-to-end method for training lightweight neural networks using multiple classifier heads. By allowing the model to determine the importance of each head and rewarding the choice of a single shallow classifier, we are…

Machine Learning · Computer Science 2020-04-20 Bartosz Wójcik , Maciej Wołczyk , Klaudia Bałazy , Jacek Tabor

Despite significant advances, deep networks remain highly susceptible to adversarial attack. One fundamental challenge is that small input perturbations can often produce large movements in the network's final-layer feature space. In this…

Machine Learning · Computer Science 2023-04-20 Maria-Florina Balcan , Avrim Blum , Dravyansh Sharma , Hongyang Zhang

We introduce a meta-learning algorithm for adversarially robust classification. The proposed method tries to be as model agnostic as possible and optimizes a dataset prior to its deployment in a machine learning system, aiming to…

Machine Learning · Computer Science 2023-02-01 Nikolaos Tsilivis , Jingtong Su , Julia Kempe

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

The history of deep learning has shown that human-designed problem-specific networks can greatly improve the classification performance of general neural models. In most practical cases, however, choosing the optimal architecture for a…

Machine Learning · Computer Science 2020-09-14 Nicolo Colombo , Yang Gao

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Cryptography and Security · Computer Science 2018-08-31 Cong Liao , Haoti Zhong , Anna Squicciarini , Sencun Zhu , David Miller

It is well-known that deep neural networks are vulnerable to adversarial attacks. Recent studies show that well-designed classification parts can lead to better robustness. However, there is still much space for improvement along this line.…

Machine Learning · Computer Science 2020-10-09 Cong Xu , Dan Li , Min Yang

It is well known that deep neural networks (DNNs) are vulnerable to adversarial attacks, which are implemented by adding crafted perturbations onto benign examples. Min-max robust optimization based adversarial training can provide a notion…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Shaokai Ye , Kaidi Xu , Sijia Liu , Jan-Henrik Lambrechts , Huan Zhang , Aojun Zhou , Kaisheng Ma , Yanzhi Wang , Xue Lin

Adversarial training is a principled approach for training robust neural networks. Despite of tremendous successes in practice, its theoretical properties still remain largely unexplored. In this paper, we provide new theoretical insights…

Machine Learning · Computer Science 2019-07-29 Yan Li , Ethan X. Fang , Huan Xu , Tuo Zhao

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we…

Machine Learning · Computer Science 2021-12-17 Motasem Alfarra , Juan C. Pérez , Ali Thabet , Adel Bibi , Philip H. S. Torr , Bernard Ghanem

The increasing access to data poses both opportunities and risks in deep learning, as one can manipulate the behaviors of deep learning models with malicious training samples. Such attacks are known as data poisoning. Recent advances in…

Machine Learning · Computer Science 2023-06-29 Wenxiao Wang , Soheil Feizi

Neural networks are easier to optimise when they have many more weights than are required for modelling the mapping from inputs to outputs. This suggests a two-stage learning procedure that first learns a large net and then prunes away…

Machine Learning · Computer Science 2019-09-10 Aidan N. Gomez , Ivan Zhang , Siddhartha Rao Kamalakara , Divyam Madaan , Kevin Swersky , Yarin Gal , Geoffrey E. Hinton

We explore the low-rank structure of the weight matrices in neural networks at the stationary points (limiting solutions of optimization algorithms) with $L2$ regularization (also known as weight decay). We show several properties of such…

Machine Learning · Computer Science 2025-08-21 Ilja Kuzborskij , Yasin Abbasi Yadkori

In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training. Unlike previous efforts in this direction, we do not rely solely on the…

Machine Learning · Computer Science 2020-03-25 Christopher M. Bender , Yang Li , Yifeng Shi , Michael K. Reiter , Junier B. Oliva

Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial training, a heuristic form of robust optimization that…

Machine Learning · Computer Science 2019-11-12 Ruiqi Gao , Tianle Cai , Haochuan Li , Liwei Wang , Cho-Jui Hsieh , Jason D. Lee

Modern machine learning and deep learning models are shown to be vulnerable when testing data are slightly perturbed. Existing theoretical studies of adversarial training algorithms mostly focus on either adversarial training losses or…

Machine Learning · Statistics 2021-04-07 Yue Xing , Qifan Song , Guang Cheng

Backdoor defenses have been studied to alleviate the threat of deep neural networks (DNNs) being backdoor attacked and thus maliciously altered. Since DNNs usually adopt some external training data from an untrusted third party, a robust…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Kuofeng Gao , Yang Bai , Jindong Gu , Yong Yang , Shu-Tao Xia

In the recent quest for trustworthy neural networks, we present Spiking Neural Network (SNN) as a potential candidate for inherent robustness against adversarial attacks. In this work, we demonstrate that adversarial accuracy of SNNs under…

Computer Vision and Pattern Recognition · Computer Science 2020-07-27 Saima Sharmin , Nitin Rathi , Priyadarshini Panda , Kaushik Roy