Gaozheng Pei

3 papers · 2025–2025 · 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 (11)

Venues

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

Top co-authors

Qianqian Xu (3) Ke Ma (3) Yingfei Sun (3) Qingming Huang (2) Shaojie Lyu (2) Pinci Yang (1) Gong Chen (1)

Research topics

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

Keywords

adversarial perturbation (2) knowledge transfer (1) data-free learning (1) query efficiency (1) diffusion model (1) adversarial defense (1) decision boundary (1) adversarial purification (1) noise injection (1) frequency domain (1) model stealing (1) defense mechanism (1) phase spectrum (1) amplitude spectrum (1) neural network (1) data-free model stealing (1) query efficient (1) hard label setting (1) substitute model (1) low-frequency component (1)

Papers

Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain ICML 2025 Divide and Conquer: Heterogeneous Noise Integration for Diffusion-based Adversarial Purification CVPR 2025 Exploring Query Efficient Data Generation Towards Data-Free Model Stealing in Hard Label Setting AAAI 2025