conftrace_

Hongyao Yu

3 papers · 2024–2026 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

ACL (1) ECCV (1) ICLR (1)

Top co-authors

Hao Fang (3) Bin Chen (3) Shu-Tao Xia (3) Yixiang Qiu (2) Meikang Qiu (1) Sijin Yu (1) Tianqu Zhuang (1) Kuofeng Gao (1) Xiaohang Sui (1) Jiawei Kong (1)

Research topics

Artificial Intelligence (2) Core AI (2) Deep Learning (1) Machine Learning (1) Security & Privacy (1) Learning Types (1) Models (1) Optimization & Theory (1) Privacy (1)

Keywords

contrastive learning (1) convex optimization (1) information bottleneck (1) generative augmentation (1) conditional mutual information (1) backdoor attack (1) model inversion attack (1) privacy leakage (1) retrieval-augmented diffusion model (1) poisoning framework (1) water-filling method (1)

Papers

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models ACL 2026 Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks ICLR 2025 A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks ECCV 2024