paper-with-me

Papers

Adversarial Detector with Robust Classifier

2022-02-05 · Takayuki Osakabe, MaungMaung AprilPyone, Sayaka Shiota, Hitoshi Kiya

Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper, we propose a novel adversarial detector, which consists of a robust classifier and a plain one, to highly detect adversarial examples. The proposed adversarial detector is carried out in accordance with the logits of plain and robust classifiers. In an experiment, the proposed detector is demonstrated to outperform a state-of-the-art detector without any robust classifier.

📄 PDF Abstract BibTeX arXiv:2202.02503

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors

2024-04-18 · Raz Lapid, Almog Dubin, Moshe Sipper

This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance…

Adversarial Examples that Fool Detectors

2017-12-07 · Jiajun Lu, Hussein Sibai, Evan Fabry

An adversarial example is an example that has been adjusted to produce a wrong label when presented to a system at test time. To date, adversarial example constructions have been demonstrated for classifiers, but not for…

Locally optimal detection of stochastic targeted universal adversarial perturbations

2020-12-08 · Amish Goel, Pierre Moulin

Deep learning image classifiers are known to be vulnerable to small adversarial perturbations of input images. In this paper, we derive the locally optimal generalized likelihood ratio test (LO-GLRT) based detector for d…

image-classificationImage Classification

On the Robustness of Malware Detectors to Adversarial Samples

2024-08-05 · Muhammad Salman, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Muhammad Ikram 외

Adversarial examples add imperceptible alterations to inputs with the objective to induce misclassification in machine learning models. They have been demonstrated to pose significant challenges in domains like image cla…

image-classificationImage ClassificationMalware Analysis

Early Methods for Detecting Adversarial Images

2016-08-01 · Dan Hendrycks, Kevin Gimpel

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 t…

BIG-bench Machine Learning