English
Related papers

Related papers: Cross-Entropy Loss and Low-Rank Features Have Resp…

200 papers

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Machine Learning · Computer Science 2020-06-08 Bai Li , Shiqi Wang , Suman Jana , Lawrence Carin

Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…

Computation and Language · Computer Science 2019-09-11 Jiawei Wu , Wenhan Xiong , William Yang Wang

Despite the high performance achieved by deep neural networks on various tasks, extensive studies have demonstrated that small tweaks in the input could fail the model predictions. This issue of deep neural networks has led to a number of…

Machine Learning · Computer Science 2022-02-22 Ming-Chang Chiu , Xuezhe Ma

Deep neural networks are susceptible to \emph{adversarial} attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks…

Machine Learning · Computer Science 2019-09-12 Gamaleldin F. Elsayed , Ian Goodfellow , Jascha Sohl-Dickstein

Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom…

Computer Science and Game Theory · Computer Science 2016-11-29 Bo Li , Yevgeniy Vorobeychik , Xinyun Chen

Recent works have shown theoretically and empirically that redundant data dimensions are a source of adversarial vulnerability. However, the inverse doesn't seem to hold in practice; employing dimension-reduction techniques doesn't exhibit…

Machine Learning · Statistics 2024-10-10 Rajdeep Haldar , Yue Xing , Qifan Song , Guang Lin

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to be accurate, calibrated and confident. We show that, as…

Machine Learning · Computer Science 2020-10-27 Jishnu Mukhoti , Viveka Kulharia , Amartya Sanyal , Stuart Golodetz , Philip H. S. Torr , Puneet K. Dokania

Generative adversarial networks (GANs) generate data based on minimizing a divergence between two distributions. The choice of that divergence is therefore critical. We argue that the divergence must take into account the hypothesis set and…

Machine Learning · Computer Science 2019-11-07 Ben Adlam , Corinna Cortes , Mehryar Mohri , Ningshan Zhang

Loss functions drive the optimization of machine learning algorithms. The choice of a loss function can have a significant impact on the training of a model, and how the model learns the data. Binary classification is one of the major…

Machine Learning · Computer Science 2022-11-02 Rayan Wali

Deep neural networks are vulnerable against adversarial examples. In this paper, we propose to train and test the networks with randomly subsampled images with high drop rates. We show that this approach significantly improves robustness…

Machine Learning · Computer Science 2019-05-02 Hossein Hosseini , Sreeram Kannan , Radha Poovendran

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen

Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions learn better representations for downstream tasks. This…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Simon Kornblith , Ting Chen , Honglak Lee , Mohammad Norouzi

An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify. While there are a number of methods proposed to generate adversarial examples for text data, it is not trivial to…

Computation and Language · Computer Science 2020-06-02 Ying Xu , Xu Zhong , Antonio Jose Jimeno Yepes , Jey Han Lau

The increasing use of deep neural networks (DNNs) has motivated a parallel endeavor: the design of adversaries that profit from successful misclassifications. However, not all adversarial examples are crafted for malicious purposes. For…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Pk Douglas , Farzad Vasheghani Farahani

Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to…

Machine Learning · Computer Science 2025-10-14 Edward Stevinson , Lucas Prieto , Melih Barsbey , Tolga Birdal

Despite strong performance in numerous applications, the fragility of deep learning to input perturbations has raised serious questions about its use in safety-critical domains. While adversarial training can mitigate this issue in…

Machine Learning · Statistics 2021-11-01 Alexander Robey , Luiz F. O. Chamon , George J. Pappas , Hamed Hassani , Alejandro Ribeiro

Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…

Machine Learning · Computer Science 2024-05-29 Yu Zhe , Rei Nagaike , Daiki Nishiyama , Kazuto Fukuchi , Jun Sakuma

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…

Machine Learning · Computer Science 2018-06-05 Pinlong Zhao , Zhouyu Fu , Ou wu , Qinghua Hu , Jun Wang

It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that adversarial perturbations, while appearing as noises, contain…

Machine Learning · Computer Science 2024-02-19 Soichiro Kumano , Hiroshi Kera , Toshihiko Yamasaki

Despite the wide empirical success of modern machine learning algorithms and models in a multitude of applications, they are known to be highly susceptible to seemingly small indiscernible perturbations to the input data known as…

Machine Learning · Statistics 2022-04-05 Adel Javanmard , Mahdi Soltanolkotabi