Zeyu Qin
8 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer π Conference Polyglot (4) π Interdisciplinary Bridge π Cross-Pollinator (10)
π
Renaissance Researcher
(6)
π₯
Unstoppable
(5)
Conferences
NIPS (5)
EMNLP (1)
ICLR (1)
ICML (1)
Top co-authors
Research topics
Keywords
backdoor attack
(2)
adversarial robustness
(2)
black-box attack
(2)
deep neural network
(2)
backdoor defense
(2)
distribution shift
(1)
gaussian noise
(1)
adversarial attack
(1)
adversarial perturbation
(1)
surrogate model
(1)
behavioral cloning
(1)
adversarial example
(1)
query-based attack
(1)
knowledge-intensive task
(1)
model purification
(1)
safety assessment
(1)
knowledge generation
(1)
open-domain question answering
(1)
knowledge-grounded dialogue
(1)
knowledge evaluation
(1)
Papers
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
ICLR 2025
Safety Reasoning with Guidelines
ICML 2025
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
NIPS 2024
Towards Stable Backdoor Purification through Feature Shift Tuning
NIPS 2023
Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators
EMNLP 2023
Imitation Learning from Imperfection: Theoretical Justifications and Algorithms
NIPS 2023
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
NIPS 2022
Random Noise Defense Against Query-Based Black-Box Attacks
NIPS 2021