Guanhong Tao

24 papers · 2018–2026 · 10 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 ↓

+10 more ↓

🗺️ Taxonomy Completionist (41) 🌍 Conference Polyglot · Gold 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

🤝 Dynamic Duo (24) 🏆 Keyword Champion (5) 🧭 Keyword Pioneer 🏆 Grand Slam 🔬 Deep Specialist (12) 🌈 Renaissance Researcher (6) 🔥 Unstoppable · Bronze ⚡ Prolific Year · Productive 💎 Century Club · Bronze 🗃️ Keyword Collector (94)

Venues

CVPR (6) NeurIPS (5) ICLR (3) AAAI (2) ECCV (2) ICML (2) ACL (1) EACL (1) EMNLP (1) WACV (1)

Top co-authors

Xiangyu Zhang (24) Guangyu Shen (15) Siyuan Cheng (12) Shiqing Ma (11) Yingqi Liu (11) Shengwei An (11) Kaiyuan Zhang (9) Qiuling Xu (8) Zhuo Zhang (6) Hanxi Guo (4)

Research topics

Artificial Intelligence (18) Machine Learning (18) Core AI (18) Learning Types · Machine Learning (13) Deep Learning (12) Application Areas (7) Learning Types · Deep Learning (7) Computer Vision (3) Analysis (3) Architectures (3) Techniques (3) Computer Science (2) Security & Privacy (2) Applications (2) Optimization & Theory (2)

Keywords

backdoor attack (11) neural network (7) adversarial learning (6) backdoor detection (5) trigger inversion (4) model security (4) adversarial attack (4) neural network security (3) image classification (2) self-supervised learning (2) neuron activation (2) ai-generated text detection (2) feature perturbation (2) adversarial defense (2) trojan detection (2) knowledge distillation (1) adversarial machine learning (1) object detection (1) adversarial robustness (1) deep reinforcement learning (1)

Papers

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026 Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis EMNLP 2025 BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens NeurIPS 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection ICLR 2024 LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024 Threat Behavior Textual Search by Attention Graph Isomorphism EACL 2024 UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening ECCV 2024 Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks ICLR 2023 Backdooring Neural Code Search ACL 2023 BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning NeurIPS 2023 Detecting Backdoors in Pre-Trained Encoders CVPR 2023 Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration NeurIPS 2023 FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning ICLR 2023 MEDIC: Remove Model Backdoors via Importance Driven Cloning CVPR 2023 ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP NeurIPS 2023 Better Trigger Inversion Optimization in Backdoor Scanning CVPR 2022 Bounded Adversarial Attack on Deep Content Features CVPR 2022 Complex Backdoor Detection by Symmetric Feature Differencing CVPR 2022 Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense ICML 2022 Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches ECCV 2022 Backdoor Scanning for Deep Neural Networks through K-Arm Optimization ICML 2021 Towards Feature Space Adversarial Attack by Style Perturbation AAAI 2021 Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples NeurIPS 2018