English
Related papers

Related papers: Boundary Adversarial Examples Against Adversarial …

200 papers

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…

Machine Learning · Computer Science 2019-10-21 Florian Tramèr , Dan Boneh

With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…

Machine Learning · Computer Science 2022-05-09 Pratik Vaishnavi , Kevin Eykholt , Amir Rahmati

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Machine Learning · Computer Science 2024-03-15 Daiwei Yu , Zhuorong Li , Lina Wei , Canghong Jin , Yun Zhang , Sixian Chan

Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at…

Machine Learning · Computer Science 2018-06-07 Liang Tong , Sixie Yu , Scott Alfeld , Yevgeniy Vorobeychik

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

Computer Vision and Pattern Recognition · Computer Science 2019-11-25 Haichao Zhang , Jianyu Wang

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

We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise,…

Machine Learning · Computer Science 2020-07-09 Amartya Sanyal , Puneet K Dokania , Varun Kanade , Philip H. S. Torr

In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions. Researchers hope that models trained on these more challenging datasets will rely…

Computation and Language · Computer Science 2021-06-03 Divyansh Kaushik , Douwe Kiela , Zachary C. Lipton , Wen-tau Yih

Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop. While adversarial training appears to enhance the robustness and safety…

Machine Learning · Computer Science 2021-03-16 Mathias Lechner , Ramin Hasani , Radu Grosu , Daniela Rus , Thomas A. Henzinger

Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy. Moreover, the training process is heavy and hence it becomes impractical to thoroughly explore the…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Haotao Wang , Tianlong Chen , Shupeng Gui , Ting-Kuei Hu , Ji Liu , Zhangyang Wang

Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework,…

Machine Learning · Computer Science 2019-05-06 Marc Khoury , Dylan Hadfield-Menell

The fragility of deep neural networks to adversarially-chosen inputs has motivated the need to revisit deep learning algorithms. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. This…

Optimization and Control · Mathematics 2020-05-05 Jacob H. Seidman , Mahyar Fazlyab , Victor M. Preciado , George J. Pappas

Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem. Previously proposed Fair Robust…

Machine Learning · Computer Science 2022-09-19 Chunyu Sun , Chenye Xu , Chengyuan Yao , Siyuan Liang , Yichao Wu , Ding Liang , XiangLong Liu , Aishan Liu

Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in…

Machine Learning · Computer Science 2024-02-06 Tianjin Huang , Shiwei Liu , Tianlong Chen , Meng Fang , Li Shen , Vlaod Menkovski , Lu Yin , Yulong Pei , Mykola Pechenizkiy

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

Recent studies have shown that robustness to adversarial attacks can be transferred across networks. In other words, we can make a weak model more robust with the help of a strong teacher model. We ask if instead of learning from a static…

Machine Learning · Computer Science 2023-02-13 Jiang Liu , Chun Pong Lau , Hossein Souri , Soheil Feizi , Rama Chellappa

Forecasting irregular time series presents significant challenges due to two key issues: the vulnerability of models to mean regression, driven by the noisy and complex nature of the data, and the limitations of traditional error-based…

Machine Learning · Computer Science 2024-12-02 Heejeong Nam , Jihyun Kim , Jimin Yeom

Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE). Nevertheless, recent studies have revealed that adversarially…

Machine Learning · Computer Science 2023-08-04 Chenhao Lin , Xiang Ji , Yulong Yang , Qian Li , Chao Shen , Run Wang , Liming Fang

Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the training process. Recent studies have demonstrated the…

Machine Learning · Computer Science 2024-10-22 Mengnan Zhao , Lihe Zhang , Jingwen Ye , Huchuan Lu , Baocai Yin , Xinchao Wang

It is becoming increasingly clear that many machine learning classifiers are vulnerable to adversarial examples. In attempting to explain the origin of adversarial examples, previous studies have typically focused on the fact that neural…

Machine Learning · Statistics 2017-11-09 Ekin D. Cubuk , Barret Zoph , Samuel S. Schoenholz , Quoc V. Le