Fangjun Huang

5 papers · 2021–2025 · 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 🗺️ Taxonomy Completionist (12)

Venues

AAAI (2) ICML (2) CVPR (1)

Top co-authors

Yunshu Dai (4) Jianwei Fei (3) Chip Hong Chang (1) Yanmei Fang (1) Yusong Wang (1) Chen Wan (1) Zhihua Xia (1) Jiachen Yang (1) Jiantao Zhou (1) Biaohua Ye (1)

Research topics

Deep Learning (4) Artificial Intelligence (3) Machine Learning (3) Core AI (3) Models (3) Computer Vision (2) Generation (2) Optimization & Theory (2) Security & Privacy (1) Application Areas (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Privacy (1)

Keywords

latent diffusion model (2) model fingerprinting (1) robustness (1) gradient descent (1) adversarial attack (1) deep neural network (1) image watermarking (1) watermark detection (1) adversarial example (1) weight encoding (1) transformer encoder (1) gradient-based attack (1) face editing (1) perturbation magnitude (1) face anti-spoofing (1) identity protection (1) model attribution (1) transfer ability (1) user accountability (1) proportional-integral-derivative controller (1)

Papers

OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting AAAI 2025 Robust Secure Swap: Responsible Face Swap With Persons of Interest Redaction and Provenance Traceability ICML 2025 Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models ICML 2025 IDGuard: Robust General Identity-centric POI Proactive Defense Against Face Editing Abuse CVPR 2024 PID-Based Approach to Adversarial Attacks AAAI 2021