conftrace_
← Authors

Siyuan Cheng

28 papers · 2021–2026 · 11 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+11 more ↓ 🌍 Conference Polyglot (11) πŸƒ Academic Marathon (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (3)
🐝 Cross-Pollinator (3) 🌈 Renaissance Researcher (7) πŸ—ΊοΈ Taxonomy Completionist (58) 🧬 Topic Evolution 🀝 Dynamic Duo (16) πŸ† Grand Slam πŸ”₯ Unstoppable (6) πŸ—ƒοΈ Keyword Collector (122) πŸ’Ž Century Club (28) ❓ The Questioner (2) ⚑ Prolific Year (9)

Conferences

EMNLP (6) AAAI (5) CVPR (5) ACL (3) ICLR (2) NIPS (2) ECCV (1) ICCV (1) ICML (1) IJCAI (1) WACV (1)

Top co-authors

Xiangyu Zhang (16) Guangyu Shen (13) Guanhong Tao (12) Ningyu Zhang (10) Shengwei An (9) Huajun Chen (9) Kaiyuan Zhang (9) Yingqi Liu (8) Shiqing Ma (8) Bozhong Tian (7)

Research topics

Privacy (2) Security & Privacy (1)

Keywords

knowledge editing (6) large language model (6) backdoor attack (6) neural network (5) adversarial learning (4) model editing (4) backdoor detection (3) adversarial attack (3) image classification (3) self-supervised learning (2) contrastive learning (2) text classification (2) ai-generated text detection (2) trojan attack (2) model security (2) diffusion model (2) trigger pattern (2) knowledge distillation (1) few-shot learning (1) object detection (1)

Papers

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026 CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI CVPR 2025 System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis EMNLP 2025 JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models ICCV 2025 MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing ACL 2024 UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening ECCV 2024 InstructEdit: Instruction-Based Knowledge Editing for Large Language Models IJCAI 2024 Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift AAAI 2024 BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens NIPS 2024 Editing Language Model-Based Knowledge Graph Embeddings AAAI 2024 To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models EMNLP 2024 EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models ACL 2024 LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning CVPR 2024 Multi-Modal Protein Knowledge Graph Construction and Applications (Student Abstract) AAAI 2023 MEDIC: Remove Model Backdoors via Importance Driven Cloning CVPR 2023 Detecting Backdoors in Pre-Trained Encoders CVPR 2023 Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration NIPS 2023 Editing Large Language Models: Problems, Methods, and Opportunities EMNLP 2023 Can We Edit Multimodal Large Language Models? EMNLP 2023 Novel Relation Detection: Discovering Unknown Relation Types via Multi-Strategy Self-Supervised Learning EMNLP 2023 FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning ICLR 2023 OntoProtein: Protein Pretraining With Gene Ontology Embedding ICLR 2022 Contrastive Demonstration Tuning for Pre-trained Language Models EMNLP 2022 Learning To Filter: Siamese Relation Network for Robust Tracking CVPR 2021 Backdoor Scanning for Deep Neural Networks through K-Arm Optimization ICML 2021 Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification AAAI 2021 Towards Feature Space Adversarial Attack by Style Perturbation AAAI 2021