English
Related papers

Related papers: Prediction Inconsistency Helps Achieve Generalizab…

200 papers

Anomaly detection is a ubiquitous and challenging task relevant across many disciplines. With the vital role communication networks play in our daily lives, the security of these networks is imperative for smooth functioning of society. To…

Cryptography and Security · Computer Science 2022-10-18 Gopikrishna Rathinavel , Nikhil Muralidhar , Timothy O'Shea , Naren Ramakrishnan

Statistical adversarial data detection (SADD) detects whether an upcoming batch contains adversarial examples (AEs) by measuring the distributional discrepancies between clean examples (CEs) and AEs. In this paper, we explore the strength…

Machine Learning · Computer Science 2025-06-09 Jiacheng Zhang , Benjamin I. P. Rubinstein , Jingfeng Zhang , Feng Liu

In recent years, neural networks have become the default choice for image classification and many other learning tasks, even though they are vulnerable to so-called adversarial attacks. To increase their robustness against these attacks,…

Machine Learning · Computer Science 2020-02-10 Hasan Ferit Eniser , Maria Christakis , Valentin Wüstholz

Adversarial examples are considered a serious issue for safety critical applications of AI, such as finance, autonomous vehicle control and medicinal applications. Though significant work has resulted in increased robustness of systems to…

Machine Learning · Statistics 2018-12-08 Andrey Malinin , Mark Gales

Adversarial robustness poses a critical challenge in the deployment of deep learning models for real-world applications. Traditional approaches to adversarial training and supervised detection rely on prior knowledge of attack types and…

Machine Learning · Computer Science 2023-08-08 Chien Cheng Chyou , Hung-Ting Su , Winston H. Hsu

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Yuhang Wu , Sunpreet S. Arora , Yanhong Wu , Hao Yang

Intrinsic susceptibility of deep learning to adversarial examples has led to a plethora of attack techniques with a broad common objective of fooling deep models. However, we find slight compositional differences between the algorithms…

Computer Vision and Pattern Recognition · Computer Science 2023-09-21 Rahul Ambati , Naveed Akhtar , Ajmal Mian , Yogesh Singh Rawat

We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks. Our approach consists in modeling the outputs of the various layers (deep features) with parametric probability…

Machine Learning · Statistics 2019-09-27 Nilesh A. Ahuja , Ibrahima Ndiour , Trushant Kalyanpur , Omesh Tickoo

Foundation models are becoming increasingly popular due to their strong generalization capabilities resulting from being trained on huge datasets. These generalization capabilities are attractive in areas such as NIR Iris Presentation…

Computer Vision and Pattern Recognition · Computer Science 2025-01-14 Juan E. Tapia , Lázaro Janier González-Soler , Christoph Busch

Adversarial machine learning is a well-studied field of research where an adversary causes predictable errors in a machine learning algorithm through precise manipulation of the input. Numerous techniques have been proposed to harden…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Pratik Vaishnavi , Kevin Eykholt , Atul Prakash , Amir Rahmati

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks.…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Xin Liu , Yichen Yang , Kun He , John E. Hopcroft

We propose an AID-purifier that can boost the robustness of adversarially-trained networks by purifying their inputs. AID-purifier is an auxiliary network that works as an add-on to an already trained main classifier. To keep it…

Machine Learning · Computer Science 2021-07-15 Duhun Hwang , Eunjung Lee , Wonjong Rhee

The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Tianhao Zhang , Shenglin Wang , Nidhal Bouaynaya , Radu Calinescu , Lyudmila Mihaylova

Deep learning models are increasingly deployed in safety-critical applications, where reliable out-of-distribution (OOD) detection is essential to ensure robustness. Existing methods predominantly rely on the penultimate-layer activations…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Shreen Gul , Mohamed Elmahallawy , Ardhendu Tripathy , Sanjay Madria

Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Scott Freitas , Shang-Tse Chen , Zijie J. Wang , Duen Horng Chau

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Yinghe Zhang , Chi Liu , Shuai Zhou , Sheng Shen , Peng Gui

Many machine learning classifiers are vulnerable to adversarial perturbations. An adversarial perturbation modifies an input to change a classifier's prediction without causing the input to seem substantially different to human perception.…

Machine Learning · Computer Science 2017-03-27 Dan Hendrycks , Kevin Gimpel

Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an…

Machine Learning · Computer Science 2021-12-24 Zhiwen Yan , Teck Khim Ng

Out-of-distribution (OOD) detection has recently gained substantial attention due to the importance of identifying out-of-domain samples in reliability and safety. Although OOD detection methods have advanced by a great deal, they are still…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Mohammad Azizmalayeri , Arshia Soltani Moakhar , Arman Zarei , Reihaneh Zohrabi , Mohammad Taghi Manzuri , Mohammad Hossein Rohban

In this paper we propose a novel method for detecting adversarial examples by training a binary classifier with both origin data and saliency data. In the case of image classification model, saliency simply explain how the model make…

Machine Learning · Computer Science 2018-03-26 Chiliang Zhang , Zhimou Yang , Zuochang Ye