English
Related papers

Related papers: Distilling Robust and Non-Robust Features in Adver…

200 papers

Adversarial examples are one of the most severe threats to deep learning models. Numerous works have been proposed to study and defend adversarial examples. However, these works lack analysis of adversarial information or perturbation,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-06 Guanlin Li , Naishan Zheng , Man Zhou , Jie Zhang , Tianwei Zhang

Existing studies have demonstrated that adversarial examples can be directly attributed to the presence of non-robust features, which are highly predictive, but can be easily manipulated by adversaries to fool NLP models. In this study, we…

Computation and Language · Computer Science 2022-06-14 Cenyuan Zhang , Xiang Zhou , Yixin Wan , Xiaoqing Zheng , Kai-Wei Chang , Cho-Jui Hsieh

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Computation and Language · Computer Science 2022-10-28 Jiahao Zhao , Wenji Mao

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this paper, we strive to explore the robust features…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Hong Wang , Yuefan Deng , Shinjae Yoo , Yuewei Lin

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of…

Machine Learning · Computer Science 2022-10-27 Huan Hua , Jun Yan , Xi Fang , Weiquan Huang , Huilin Yin , Wancheng Ge

Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be directly attributed to the presence of…

Machine Learning · Statistics 2019-08-13 Andrew Ilyas , Shibani Santurkar , Dimitris Tsipras , Logan Engstrom , Brandon Tran , Aleksander Madry

The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…

Machine Learning · Computer Science 2024-05-07 Ang Li , Yifei Wang , Yiwen Guo , Yisen Wang

Adversarial fine-tuning methods enhance adversarial robustness via fine-tuning the pre-trained model in an adversarial training manner. However, we identify that some specific latent features of adversarial samples are confused by…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Nuoyan Zhou , Dawei Zhou , Decheng Liu , Nannan Wang , Xinbo Gao

Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…

Machine Learning · Computer Science 2019-09-11 Byunggill Joe , Sung Ju Hwang , Insik Shin

Over the past decade, numerous theories have been proposed to explain the widespread vulnerability of deep neural networks to adversarial evasion attacks. Among these, the theory of non-robust features proposed by Ilyas et al. has been…

Machine Learning · Computer Science 2026-01-05 Jennifer Crawford , Amol Khanna , Fred Lu , Amy R. Wagoner , Stella Biderman , Andre T. Nguyen , Edward Raff

We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks can improve upon adversarial training. Our evaluation under a…

Machine Learning · Computer Science 2021-07-14 Iryna Korshunova , David Stutz , Alexander A. Alemi , Olivia Wiles , Sven Gowal

Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that…

Machine Learning · Computer Science 2021-02-11 Jacob M. Springer , Melanie Mitchell , Garrett T. Kenyon

Recent work has put forth the hypothesis that adversarial vulnerabilities in neural networks are due to them overusing "non-robust features" inherent in the training data. We show empirically that for PGD-attacks, there is a training stage…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Zuowen Wang , Leo Horne

In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…

Machine Learning · Computer Science 2023-03-27 Jongheon Jeong , Sihyun Yu , Hankook Lee , Jinwoo Shin

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also…

Machine Learning · Computer Science 2021-03-24 Jaekyeom Kim , Minjung Kim , Dongyeon Woo , Gunhee Kim

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…

Computation and Language · Computer Science 2024-10-07 Hosein Mohebbi , Grzegorz Chrupała , Willem Zuidema , Afra Alishahi , Ivan Titov

Recent breakthroughs in the field of deep learning have led to advancements in a broad spectrum of tasks in computer vision, audio processing, natural language processing and other areas. In most instances where these tasks are deployed in…

Machine Learning · Computer Science 2019-05-28 Daanish Ali Khan , Linhong Li , Ninghao Sha , Zhuoran Liu , Abelino Jimenez , Bhiksha Raj , Rita Singh

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen types of adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Dawei Zhou , Tongliang Liu , Bo Han , Nannan Wang , Chunlei Peng , Xinbo Gao

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) has shown excellent high performance in defending against adversarial examples. Recent studies demonstrate that examples are not equally important to the final robustness of models during AT, that is, the so-called…

Machine Learning · Computer Science 2022-06-27 Mengting Xu , Tao Zhang , Zhongnian Li , Daoqiang Zhang
‹ Prev 1 2 3 10 Next ›