conftrace_
← Authors

Yufei Han

14 papers · 2016–2026 · 8 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+8 more ↓ πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (9) 🌈 Renaissance Researcher (6) πŸ—ΊοΈ Taxonomy Completionist (33)
🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (9) πŸ† Grand Slam 🧬 Topic Evolution πŸ’Ž Century Club (13) πŸ”₯ Unstoppable (6) πŸ—ƒοΈ Keyword Collector (59)

Conferences

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

Top co-authors

Xiangliang Zhang (8) Yujun Zhou (5) Hongyan Bao (4) Boxin Shi (3) Haomin Zhuang (3) Yun Shen (2) Zhenwen Liang (2) Junge Zhang (2) Zhanyu Ma (2) Jing Cui (2)

Keywords

adversarial attack (3) adversarial learning (3) backdoor attack (3) evasion attack (2) federated learning (2) model poisoning (2) reflective surface (2) polarimetric imaging (2) large language model (2) multi-label classification (1) surface reconstruction (1) evaluation framework (1) agent learning (1) robust learning (1) in-context learning (1) reinforcement learning (1) privacy-preserving learning (1) neural network optimization (1) machine teaching (1) privacy preservation (1)

Papers

Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMs AAAI 2026 Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study EMNLP 2025 PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction ICCV 2025 Defending Jailbreak Prompts via In-Context Adversarial Game EMNLP 2024 BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning AAAI 2024 NeRSP: Neural 3D Reconstruction for Reflective Objects with Sparse Polarized Images CVPR 2024 Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data ICML 2024 Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated Learning AAAI 2023 Towards Efficient and Domain-Agnostic Evasion Attack with High-Dimensional Categorical Inputs AAAI 2023 Towards Understanding the Robustness Against Evasion Attack on Categorical Data ICLR 2022 Learning to dehaze with polarization NIPS 2021 Characterizing the Evasion Attackability of Multi-label Classifiers AAAI 2021 Robust Federated Learning via Collaborative Machine Teaching AAAI 2020 Partially Supervised Graph Embedding for Positive Unlabelled Feature Selection IJCAI 2016