Chunsheng Xin

6 papers · 2018–2024 · 4 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 ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird

Venues

AAAI (3) ECCV (1) ICCV (1) IJCAI (1)

Top co-authors

Hongyi Wu (6) Rui Ning (4) Liuwan Zhu (3) Jiang Li (3) Chonggang Wang (2) Qiao Zhang (2) Tao Xiang (1) Tran V. Phuong (1) Cong Wang (1)

Research topics

Machine Learning (4) Application Areas (4) Artificial Intelligence (3) Deep Learning (3) Core AI (3) Architectures (2) Learning Types · Deep Learning (2) Learning Types · Machine Learning (1) Optimization & Theory (1)

Keywords

deep neural network (2) backdoor detection (2) data poisoning (1) multimodal learning (1) efficient computing (1) mutual information (1) feature space (1) mutual information maximization (1) collaborative learning (1) backdoor attack (1) adversarial attack (1) adversarial defense (1) vision-language model (1) cryptographic primitive (1) homomorphic encryption (1) privacy-preserving inference (1) trigger detection (1) neural network (1) multimodal defense (1) neural backdoor attack (1)

Papers

SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly AAAI 2024 United We Stand: Accelerating Privacy-Preserving Neural Inference by Conjunctive Optimization with Interleaved Nexus AAAI 2024 Hibernated Backdoor: A Mutual Information Empowered Backdoor Attack to Deep Neural Networks AAAI 2022 Most and Least Retrievable Images in Visual-Language Query Systems ECCV 2022 CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks ICCV 2021 GELU-Net: A Globally Encrypted, Locally Unencrypted Deep Neural Network for Privacy-Preserved Learning IJCAI 2018