Zhaohan Xi
5 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(11)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
EMNLP (1)
ICCV (1)
ICLR (1)
NAACL (1)
NIPS (1)
Top co-authors
Keywords
backdoor attack
(2)
adversarial defense
(2)
few-shot learning
(2)
self-supervised learning
(1)
harmful content
(1)
safety alignment
(1)
model alignment
(1)
pre-trained language model
(1)
data curation
(1)
model customization
(1)
trigger inversion
(1)
large language model
(1)
representation invariance
(1)
harmful content mitigation
(1)
backdoor removal
(1)
adversarial prompt tuning
(1)
soft token
(1)
poisoning sample
(1)
safety compromise
(1)
representation learning
(1)
Papers
Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise
EMNLP 2025
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
NAACL 2024
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
NIPS 2023
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
ICCV 2023
The Dark Side of AutoML: Towards Architectural Backdoor Search
ICLR 2023