Poster Sat, Sep 12, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 353

Improving Adversarial Robustness via Activation Amplification and Attenuation

Taïga Gonçalves ⋅ Yongsong Huang ⋅ Tomo Miyazaki ⋅ Shinichiro Omachi

Keywords: Federated, Continual & Efficient Learning; Model Security