Xixiang Lyu
4 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (4) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge π Cross-Pollinator (12)
πΊοΈ
Taxonomy Completionist
(10)
π
Grand Slam
Conferences
AAAI (1)
ICLR (1)
ICML (1)
NIPS (1)
Top co-authors
Research topics
Keywords
backdoor attack
(3)
adversarial learning
(2)
backdoor defense
(2)
model unlearning
(1)
machine unlearning
(1)
deep neural network
(1)
pretrained language model
(1)
gradient ascent
(1)
embedding analysis
(1)
neuron pruning
(1)
poisoned datum
(1)
clean model
(1)
token unlearning
(1)
model compression
(1)
anti-backdoor learning
(1)
model security
(1)
neural network security
(1)
Papers
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
AAAI 2025
Reconstructive Neuron Pruning for Backdoor Defense
ICML 2023
Anti-Backdoor Learning: Training Clean Models on Poisoned Data
NIPS 2021
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
ICLR 2021