Harry Cheng

3 papers · 2025–2025 · 2 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 (10)

Venues

ICCV (2) IJCAI (1)

Top co-authors

Tianyi Wang (2) Yangyang Guo (1) Xin-Shun Xu (1) Xin Luo (1) Ming Yang (1) Xiao Zhang (1) Weili Guan (1) Liqiang Nie (1) Qingpei Guo (1) Tian Gan (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Application Areas (2) Core AI (2) Learning Types · Machine Learning (2) Computer Vision (1) Deep Learning (1) Analysis (1) Core Methods (1) Learning Types · Deep Learning (1)

Keywords

deepfake detection (2) binary classification (1) prototype learning (1) face recognition (1) adversarial perturbation (1) multimodal large language model (1) face swapping (1) social bia (1) real face concept (1) model fairness (1) identity protection (1) identity cloaking (1) proactive perturbation (1) domain generalization (1) proactive defense (1)

Papers

Learning Real Facial Concepts for Independent Deepfake Detection IJCAI 2025 NullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping ICCV 2025 Social Debiasing for Fair Multi-modal LLMs ICCV 2025