Page 71 - AI for Good-Innovate for Impact

AI for Good-Innovate for Impact

13�4� Sequence diagram 13-Changan

13�5� References

[1]. CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the
Wild. Available online:https:// dblp .org/ rec/ conf/ iclr/ ZhangFDG19 .html

[2]. Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World.
Available online:https:// ieeexplore .ieee .org/ document/ 9577412/

[3]. FCA: Learning a 3D Full-Coverage Vehicle Camouflage for Multi-View Physical Adversarial
Attack. Available online:https:// ojs .aaai .org/ index .php/ AAAI/ article/ view/ 20141

[4]. Towards highly transferable 3d physical camouflage for universal and robust vehicle evasion.
Available online:https:// dblp .org/ rec/ journals/ corr/ abs -2308 -07009 .html
[5]. Adversarial Patch Attacks on Monocular Depth Estimation Networks

Available online:https:// ieeexplore .ieee .org/ document/ 9207958

[6]. APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for
Autonomous Navigation� Available online:https:// dblp .org/ rec/ journals/ corr/ abs -2303 -01351
.html

[7]. Saam: Stealthy adversarial attack on monocular depth estimation. Available online: https://
ieeexplore .ieee .org/ document/ 10388324

[8]. Physical attack on monocular depth estimation with optimal adversarial patches. Available
online: https:// link .springer .com/ chapter/ 10 .1007/ 978 -3 -031 -19839 -7 _30

[9]. Dta: Physical camouflage attacks using differentiable transformation network. Available
online: https:// ieeexplore .ieee .org/ document/ 9880039

55