Shengwei An
13 papers · 2021–2026 · 8 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (22) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Grand Slam
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(50)
Top co-authors
Research topics
Artificial Intelligence
(9)
Machine Learning
(9)
Core AI
(9)
Application Areas
(6)
Deep Learning
(4)
Learning Types Β· Machine Learning
(4)
Optimization & Theory
(3)
Security & Privacy
(2)
Learning Types Β· Deep Learning
(2)
Privacy
(2)
Techniques
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Analysis
(1)
Keywords
backdoor attack
(9)
model security
(3)
trigger inversion
(3)
adversarial learning
(3)
neural network
(2)
adversarial defense
(2)
backdoor detection
(2)
text classification
(1)
neural network security
(1)
image classification
(1)
distribution shift
(1)
black-box attack
(1)
generative model
(1)
diffusion model
(1)
context inference
(1)
neural network optimization
(1)
watermark detection
(1)
surrogate model
(1)
knowledge distillation
(1)
adversarial perturbation
(1)
Papers
Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening
WACV 2026
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis
EMNLP 2025
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
AAAI 2024
Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks
AAAI 2024
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
CVPR 2024
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
ECCV 2024
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
NeurIPS 2023
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
ICLR 2023
MEDIC: Remove Model Backdoors via Importance Driven Cloning
CVPR 2023
An Invisible Black-Box Backdoor Attack through Frequency Domain
ECCV 2022
Better Trigger Inversion Optimization in Backdoor Scanning
CVPR 2022
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
ICML 2022
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
ICML 2021