Yingqi Liu
15 papers · 2018–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (8) π Renaissance Researcher (7) π Conference Polyglot (6) πΊοΈ Taxonomy Completionist (20)
πΊοΈ
Taxonomy Completionist
(20)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(12)
π
Grand Slam
π§¬
Topic Evolution
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(55)
π
Century Club
(15)
π₯
Unstoppable
(6)
Conferences
CVPR (7)
ICLR (2)
ICML (2)
NIPS (2)
AAAI (1)
WACV (1)
Top co-authors
Research topics
Keywords
backdoor attack
(7)
neural network
(5)
trigger inversion
(4)
adversarial learning
(4)
backdoor detection
(3)
neural network security
(2)
trigger pattern
(2)
trojan detection
(2)
trojan attack
(2)
neuron activation
(2)
adversarial defense
(2)
deep neural network
(2)
model security
(2)
adversarial attack
(1)
feature space
(1)
loss landscape
(1)
non-convex optimization
(1)
image classification
(1)
face recognition
(1)
image classifier
(1)
Papers
Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening
WACV 2026
Understanding the Stability-based Generalization of Personalized Federated Learning
ICLR 2025
Decentralized Directed Collaboration for Personalized Federated Learning
CVPR 2024
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
CVPR 2024
Make Landscape Flatter in Differentially Private Federated Learning
CVPR 2023
Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
NIPS 2023
MEDIC: Remove Model Backdoors via Importance Driven Cloning
CVPR 2023
Detecting Backdoors in Pre-Trained Encoders
CVPR 2023
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
ICLR 2023
Complex Backdoor Detection by Symmetric Feature Differencing
CVPR 2022
Better Trigger Inversion Optimization in Backdoor Scanning
CVPR 2022
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense
ICML 2022
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
AAAI 2021
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
ICML 2021
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
NIPS 2018