Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Mingli Zhu, Shaokui Wei, Hongyuan Zha, Baoyuan Wu. Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

This author has not been identified. Look up 'Mingli Zhu' in GoogleThis author has not been identified. Look up 'Shaokui Wei' in GoogleThis author has not been identified. Look up 'Hongyuan Zha' in GoogleThis author has not been identified. Look up 'Baoyuan Wu' in Google

runs on WebDSL