Adversarial catoptric light: An effective, stealthy and robust physical‐world attack to DNNs

Abstract Recent studies have demonstrated that finely tuned deep neural networks (DNNs) are susceptible to adversarial attacks. Conventional physical attacks employ stickers as perturbations, achieving robust adversarial effects but compromising stealthiness. Recent innovations utilise light beams,...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Chengyin Hu, Weiwen Shi, Ling Tian, Wen Li
Format:	Artigo
Jezik:	Inglês
Izdano:	Wiley 2024-08-01
Serija:	IET Computer Vision
Teme:	AdvCL DNNs effectiveness physical attacks robustness stealthiness
Online dostop:	https://doi.org/10.1049/cvi2.12264
Oznake:	Označite Brez oznak, prvi označite!