Shengwei An
13 papers · 2021–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Renaissance Researcher (7) π Interdisciplinary Bridge π Conference Polyglot (8) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (22)
π£
Hot Topic Early Bird
π
Conference Polyglot
(8)
π
Academic Marathon
(5)
π
Grand Slam
π§¬
Topic Evolution
π€
Dynamic Duo
(11)
π
Century Club
(13)
π₯
Unstoppable
(6)
Conferences
CVPR (3)
AAAI (2)
ECCV (2)
ICML (2)
EMNLP (1)
ICLR (1)
NIPS (1)
WACV (1)
Top co-authors
Research topics
Keywords
backdoor attack
(8)
adversarial learning
(3)
trigger inversion
(3)
model security
(3)
adversarial defense
(2)
neural network
(2)
backdoor detection
(2)
object detection
(1)
black-box attack
(1)
text classification
(1)
distribution shift
(1)
generative model
(1)
diffusion model
(1)
neural network security
(1)
watermark detection
(1)
neural network optimization
(1)
surrogate model
(1)
context inference
(1)
ai-generated text detection
(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
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
ECCV 2024
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
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
NIPS 2023
MEDIC: Remove Model Backdoors via Importance Driven Cloning
CVPR 2023
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
ICLR 2023
Better Trigger Inversion Optimization in Backdoor Scanning
CVPR 2022
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
ICML 2022
An Invisible Black-Box Backdoor Attack through Frequency Domain
ECCV 2022
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
ICML 2021