English
Related papers

Related papers: Adversarial Robustness Overestimation and Instabil…

200 papers

Although fast adversarial training has demonstrated both robustness and efficiency, the problem of "catastrophic overfitting" has been observed. This is a phenomenon in which, during single-step adversarial training, the robust accuracy…

Machine Learning · Computer Science 2020-12-16 Hoki Kim , Woojin Lee , Jaewook Lee

Overfitting widely exists in adversarial robust training of deep networks. An effective remedy is adversarial weight perturbation, which injects the worst-case weight perturbation during network training by maximizing the classification…

Machine Learning · Computer Science 2022-05-31 Chaojian Yu , Bo Han , Mingming Gong , Li Shen , Shiming Ge , Bo Du , Tongliang Liu

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine Learning · Computer Science 2018-02-14 Angus Galloway , Graham W. Taylor , Medhat Moussa

We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. We formulate the training problem as a joint optimization problem with both empirical…

Machine Learning · Computer Science 2021-06-08 Jiameng Fan , Wenchao Li

He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional…

Machine Learning · Computer Science 2019-10-22 Dan Hendrycks , Kimin Lee , Mantas Mazeika

Many of the successes of machine learning are based on minimizing an averaged loss function. However, it is well-known that this paradigm suffers from robustness issues that hinder its applicability in safety-critical domains. These issues…

Machine Learning · Computer Science 2022-06-09 Alexander Robey , Luiz F. O. Chamon , George J. Pappas , Hamed Hassani

Despite breakthrough performance, modern learning models are known to be highly vulnerable to small adversarial perturbations in their inputs. While a wide variety of recent \emph{adversarial training} methods have been effective at…

Machine Learning · Computer Science 2020-02-26 Adel Javanmard , Mahdi Soltanolkotabi , Hamed Hassani

While deep learning has led to remarkable results on a number of challenging problems, researchers have discovered a vulnerability of neural networks in adversarial settings, where small but carefully chosen perturbations to the input can…

Neural and Evolutionary Computing · Computer Science 2018-11-26 Edward Grefenstette , Robert Stanforth , Brendan O'Donoghue , Jonathan Uesato , Grzegorz Swirszcz , Pushmeet Kohli

In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model…

Computer Vision and Pattern Recognition · Computer Science 2019-08-02 Jianyu Wang , Haichao Zhang

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

Robotics · Computer Science 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This…

Machine Learning · Computer Science 2025-07-01 Joshua C. Zhao , Saurabh Bagchi

To evaluate the robustness of non-classifier models, we propose probabilistic local equivalence, based on the notion of randomized smoothing, as a way to quantitatively evaluate the robustness of an arbitrary function. In addition, to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Jacob Bond , Andrew Lingg

Adversarially robust classifiers possess a trait that non-robust models do not -- Perceptually Aligned Gradients (PAG). Their gradients with respect to the input align well with human perception. Several works have identified PAG as a…

Computer Vision and Pattern Recognition · Computer Science 2023-08-10 Roy Ganz , Bahjat Kawar , Michael Elad

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Fatemeh Amerehi , Patrick Healy

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

Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the…

Machine Learning · Computer Science 2022-03-04 Mo Zhou , Vishal M. Patel

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Machine Learning · Computer Science 2022-11-28 Muhammad Zaid Hameed , Beat Buesser

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

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to…

Machine Learning · Computer Science 2019-10-29 Chengzhi Mao , Ziyuan Zhong , Junfeng Yang , Carl Vondrick , Baishakhi Ray

Contrastive divergence is a popular method of training energy-based models, but is known to have difficulties with training stability. We propose an adaptation to improve contrastive divergence training by scrutinizing a gradient term that…

Machine Learning · Computer Science 2021-06-14 Yilun Du , Shuang Li , Joshua Tenenbaum , Igor Mordatch