Zeyu Qin
8 papers
· 2021–2025
· 4 conferences
· across top CS/AI conferences
Achievements
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
Safety Reasoning with Guidelines
ICML 2025