conftrace_
← Authors

Leo Yu Zhang

25 papers · 2022–2026 · 8 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+10 more ↓ 🐝 Cross-Pollinator (15) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (8) 🌈 Renaissance Researcher (5)
🌈 Renaissance Researcher (5) πŸ—ΊοΈ Taxonomy Completionist (30) 🀝 Dynamic Duo (15) πŸ”¬ Deep Specialist (13) πŸ† Grand Slam πŸ† Keyword Champion πŸ’Ž Century Club (22) πŸ”₯ Unstoppable (5) ⚑ Prolific Year (7) πŸ—ƒοΈ Keyword Collector (104)

Conferences

AAAI (10) IJCAI (6) CVPR (2) ICML (2) NIPS (2) EMNLP (1) ICCV (1) ICLR (1)

Top co-authors

Shengshan Hu (16) Minghui Li (9) Yanjun Zhang (8) Ziqi Zhou (7) Hai Jin (6) Xianlong Wang (4) Hangtao Zhang (4) Yichen Wang (4) Lulu Xue (4) Shirui Pan (3)

Research topics

Privacy (2)

Keywords

adversarial attack (8) backdoor attack (6) federated learning (5) model poisoning (3) universal adversarial perturbation (3) adversarial learning (3) object detection (3) adversarial defense (3) adversarial example (3) adversarial perturbation (2) poisoning attack (2) autonomous driving (2) self-supervised learning (2) gradient inversion attack (2) optimal transport (1) model robustness (1) metric learning (1) style transfer (1) image segmentation (1) model extraction attack (1)

Papers

Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification AAAI 2026 Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure AAAI 2026 Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation AAAI 2026 BiMark: Unbiased Multilayer Watermarking for Large Language Models ICML 2025 MMGIA: Gradient Inversion Attack Against Multimodal Federated Learning via Intermodal Correlation IJCAI 2025 NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors AAAI 2025 Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization AAAI 2025 Detecting and Corrupting Convolution-based Unlearnable Examples AAAI 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment EMNLP 2025 BadRobot: Jailbreaking Embodied LLM Agents in the Physical World ICLR 2025 Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach IJCAI 2025 Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World IJCAI 2024 Conditional Backdoor Attack via JPEG Compression AAAI 2024 Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation AAAI 2024 DarkSAM: Fooling Segment Anything Model to Segment Nothing NIPS 2024 IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency ICML 2024 Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks AAAI 2024 DarkFed: A Data-Free Backdoor Attack in Federated Learning IJCAI 2024 Downstream-agnostic Adversarial Examples ICCV 2023 PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models against Adversarial Examples AAAI 2023 Towards Self-Interpretable Graph-Level Anomaly Detection NIPS 2023 Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning IJCAI 2023 Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection IJCAI 2022 Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer CVPR 2022