21 citations · 21 across the 2 of their papers we have counts for
2 papers
cs.CL2023
The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples
Heng Yang, Ke Li
Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial exa…
cs.CR2022★ 21 cited
Defend Data Poisoning Attacks on Voice Authentication
Ke Li, Cameron Baird, Dan Lin
With the advances in deep learning, speaker verification has achieved very high accuracy and is gaining popularity as a type of biometric authentication option in many scenes of ou…