Article

Image Synthesis-based Backdoor Attack Approach in the Face Classification Task

2023-09-08

Abstract excerpt

Although deep neural networks (DNNs) are applied in various fields owing to their remarkable performance, recent studies have reported that DNN models are vulnerable to backdoor attacks. They generated backdoored images by adding a backdoor trigger in original training images that activates the backdoor attack. However, most of previous attack methods are noticeable, not natural to the human eye, and easily detect...

Topics

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

Identifiers and source

Literature Corpus work: 8e50db9d-d81b-5ab1-914b-30dd8adfb959
DOI: 10.21203/rs.3.rs-3322851/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Image Synthesis-based Backdoor Attack Approach in the Face Classification TaskDOI 10.21203/rs.3.rs-3322851/v1Read

Beyond AI: Fooling DNN Model in Physical WorldSemantic proximity Read

Generation and Countermeasures of Adversarial Examples on Vision: A SurveySemantic proximity Read

Color-channel Adversarial Attack with Resolution based CamouflagingSemantic proximity Read

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

Fast Fake – easy to train Face Swap modelSemantic proximity Read

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

Classifying Real and AI-Generated Images Using Fine-Tuned ResNet50.Semantic proximity Read

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

An Attention-Erasing Stripe Pyramid Network for Face Forgery DetectionSemantic proximity Read

A Novel Deepfake Detection Framework using Audio-Video-Textual FeaturesSemantic proximity Read

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

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