adversarial-explainable-ai
💡 Adversarial attacks on explanations and how to defend them
- 336
- CC-BY-SA-4.0
- 24 mo ago
💡 Adversarial attacks on explanations and how to defend them
[ASE 2025 Tool Demo] WIBE: An Extensible Open Source Framework for Evaluating Imperceptibility and Robustness of Invisible Image Watermarks (WARP Benchmark paper coming soon)