hbaniecki / adversarial-explainable-ai

💡 Adversarial attacks on explanations and how to defend them

https://doi.org/10.1016/j.inffus.2024.102303

Focus-Shifting Attack: An Adversarial Attack That Retains Saliency Map Information and Manipulates Model Explanations

hbaniecki opened this issue a year ago · comments

Hubert Baniecki commented a year ago

https://doi.org/10.1109/TR.2023.3303923