ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Shaokui Wei

Shaokui Wei

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

6

papers

389

total citations

papers (6)

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

NEURIPS 2022arXiv

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

NEURIPS 2023arXiv

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

NEURIPS 2023arXiv

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

Backdoor Mitigation by Distance-Driven Detoxification