Article

Generation and Countermeasures of Adversarial Examples on Vision: A Survey

2023-09-04

Abstract excerpt

Recent studies have found that deep learning models are vulnerable to adversarial examples, demonstrating that applying a certain imperceptible perturbation on clean examples can effectively deceive the well-trained and high-accuracy deep learning models. Moreover, the adversarial examples can achieve a considerable level of certainty with the attacked label. In contrast, human could barely discern the difference...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 5d2f685a-0994-5bfe-afec-ee38e3c9d8bc
DOI: 10.21203/rs.3.rs-3312403/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Generation and Countermeasures of Adversarial Examples on Vision: A SurveyDOI 10.21203/rs.3.rs-3312403/v1Read

Transient Deception: Recent Advances and Trends in Short-Lived Adversarial ExamplesSemantic proximity Read

Chained Dual-GAN: A Generalized Defense against Adversarial AttacksSemantic proximity Read

Beyond AI: Fooling DNN Model in Physical WorldSemantic proximity Read

What do adversarial images tell us about human vision?Semantic proximity Read

Improving Transferability of Adversarial Examples with Mixed-Representation AttackSemantic proximity Read

Color-channel Adversarial Attack with Resolution based CamouflagingSemantic proximity Read

Natural Images Allow Universal Adversarial Attacks on Medical Image Classification Using Deep Neural Networks With Transfer LearningSemantic proximity Read

Functionality-preserving Adversarial Machine Learning For Robust Classification In Cybersecurity And Intrusion Detection Domains: A SurveySemantic proximity Read

Imperceptible Adversarial Attacks against Traffic Scene RecognitionSemantic proximity Read

How Adversarial attacks affect Deep Neural Networks Detecting COVID-19?Semantic proximity Read

Robust deep learning object recognition models rely on low frequency information in natural imagesSemantic proximity Read

Optimally Configured Generative Adversarial Networks to Distinguish Real and AI- Generated Human FacesSemantic proximity Read