Zeyang Sha
3 papers · 2023–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Bronze
π
Interdisciplinary Bridge Β· Gold
πΊοΈ
Taxonomy Completionist
(10)
π£
Hot Topic Early Bird
β
The Questioner
Top co-authors
Research topics
Keywords
large language model
(2)
contrastive learning
(1)
reinforcement learning
(1)
direct preference optimization
(1)
self-supervised learning
(1)
adversarial attack
(1)
privacy leakage
(1)
prompt injection
(1)
model stealing
(1)
security attack
(1)
image encoder
(1)
reasoning enhancement
(1)
conversation reconstruction
(1)
attack surface
(1)
representation learning
(1)
tool hallucination
(1)
Papers
The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
ACL 2026
Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
EMNLP 2024
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
CVPR 2023