intellisec/xai-backdoors

Disguising Attacks with Explanation-Aware Backdoors (IEEE S&P 2023)

Python

Issues

How did you train the 'Fooling Explanations' with different shapes?
#2 opened 7 months ago by kitaharasetusna
4
error raised when I try to use manipulated models
#1 opened 7 months ago by bamrainboo
2