Reference

B. G. Doan, M. Xue, S. Ma, E. Abbasnejad and D. C. Ranasinghe, "TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems," in IEEE Transactions on Information Forensics and Security, 2022, doi: 10.1109/TIFS.2022.3198857.

Link to the research paper: TnTattacks

Bibtex

@ARTICLE{9856683,
  author={Doan, Bao Gia and Xue, Minhui and Ma, Shiqing and Abbasnejad, Ehsan and C. Ranasinghe, Damith},
  journal={IEEE Transactions on Information Forensics and Security}, 
  title={TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems}, 
  year={2022},
  volume={17},
  pages={3816-3830},
  doi={10.1109/TIFS.2022.3198857}}

Physical World Deployment Demonstration Videos

Summary

Targeted Attacks on the PubFig Classification Task

• The effectiveness of an example flower TnT
• The robustness of an example flower TnT

Targeted Attacks on ImageNet Large Scale Visual Recognition Task

• The effectiveness of an example flower TnT
• The effectiveness and robustness of miscellaneous examples of flower TnTs
• The effectiveness of a patch trigger
• The robustness of a patch trigger

Demo Videos

Targeted Attack with an input-agnostic TnT, an example flower, from the TnT Generator - PubFig Face Recognition Task

The effectiveness of an example flower TnT

The robustness of an example flower TnT

Targeted Attack with an Input-Agnostic flower Trigger from the TnT Generator - ImageNet classification task

The effectiveness of an example flower TnT

The effectiveness and robustness of miscellaneous examples of flower TnTs

Targeted Attack with an Input-Agnostic Patch from the Adversarial Patch Generator - ImageNet classification task

The effectiveness of a patch trigger

The robustness of a patch trigger