4 papers · 1 filter
Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3
Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protect…
Learning Transferable Skills using Goal-Conditioned Bisimulation
Mohammad Amin Abbasfar, Farbod Azimmohseni, Mohammad Hossein Rohban
Unsupervised skill discovery has emerged as a promising approach for leveraging reward-free datasets to pretrain general-purpose policies. However, current skill discovery methods…
SORA: Free Second-Order Attacks in Fast Adversarial Training
Mazdak Teymourian, Ramtin Moslemi, Farzan Rahmani +1
Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-step variants, where robustness…
Generalization and Membership Inference Attack a Practical Perspective
Fateme Rahmani, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban
With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previously accepted assumptions. In…