Yixiang Qiu
3 papers · 2024–2025 · 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
contrastive learning
(1)
adversarial learning
(1)
convex optimization
(1)
text classification
(1)
information bottleneck
(1)
text generation
(1)
conditional mutual information
(1)
adversarial evasion
(1)
model inversion attack
(1)
privacy leakage
(1)
paraphrase attack
(1)
machine-generated text
(1)
text detector
(1)
large language model
(1)
llm-generated text
(1)
water-filling method
(1)
Papers
Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks
ICLR 2025
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
EMNLP 2025
A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks
ECCV 2024