conftrace_
← Authors

Siyuan Liang

30 papers · 2019–2026 · 10 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+11 more ↓ 🌍 Conference Polyglot (10) πŸƒ Academic Marathon (6) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (9)
🐝 Cross-Pollinator (9) πŸ—ΊοΈ Taxonomy Completionist (48) 🀝 Dynamic Duo (15) πŸ† Grand Slam πŸ”¬ Deep Specialist (16) 🧬 Topic Evolution ⚑ Prolific Year (8) ❓ The Questioner πŸ—ƒοΈ Keyword Collector (106) πŸ”₯ Unstoppable (7) πŸ’Ž Century Club (26)

Conferences

AAAI (8) CVPR (5) ICCV (5) ICLR (3) ACL (2) ECCV (2) IJCAI (2) EMNLP (1) ICML (1) NIPS (1)

Top co-authors

Xiaochun Cao (15) Aishan Liu (11) Dacheng Tao (9) Xiaojun Jia (6) Baoyuan Wu (5) Jiawei Liang (5) Jingzhi Li (4) Xianglong Liu (4) Mingli Zhu (3) Xingxing Wei (3)

Research topics

Privacy (3)

Keywords

adversarial example (6) backdoor attack (6) adversarial attack (5) object detection (5) adversarial learning (3) backdoor defense (3) large language model (3) physical attack (2) reinforcement learning (2) 3d point cloud (2) model security (2) multimodal learning (2) trigger pattern (2) adversarial camouflage (2) autonomous driving (2) adversarial training (2) image classification (2) point cloud (2) black-box attack (2) imperceptible perturbation (2)

Papers

Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles AAAI 2026 SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs AAAI 2026 Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees ACL 2026 Multi-Modal Fact Knowledge Generation for Imbalanced Cross-Source Entity Alignment AAAI 2026 Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance ICCV 2025 ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models ACL 2025 NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models ICLR 2025 Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift CVPR 2025 Interpreting Object-level Foundation Models via Visual Precision Search CVPR 2025 Physical Adversarial Camouflage Through Gradient Calibration and Regularization IJCAI 2025 ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks ICML 2025 Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models EMNLP 2025 3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation ICCV 2025 Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion ICCV 2025 CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks ICCV 2025 Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack NIPS 2024 Correlation Matching Transformation Transformers for UHD Image Restoration AAAI 2024 Does Few-Shot Learning Suffer from Backdoor Attacks? AAAI 2024 Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning AAAI 2024 BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning CVPR 2024 Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds CVPR 2024 Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection ICLR 2024 Less is More: Fewer Interpretable Region via Submodular Subset Selection ICLR 2024 Improving Robust Fariness via Balance Adversarial Training AAAI 2023 Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization AAAI 2023 Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization CVPR 2023 A Large-Scale Multiple-Objective Method for Black-Box Attack against Object Detection ECCV 2022 Parallel Rectangle Flip Attack: A Query-Based Black-Box Attack Against Object Detection ICCV 2021 Efficient Adversarial Attacks for Visual Object Tracking ECCV 2020 Transferable Adversarial Attacks for Image and Video Object Detection IJCAI 2019