Qiongkai Xu
Australian National University
H-index: 13
Oceania-Australia
Top articles of Qiongkai Xu
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Backdoor Attack on Multilingual Machine Translation | arXiv preprint arXiv:2404.02393 | Jun Wang Qiongkai Xu Xuanli He Benjamin IP Rubinstein Trevor Cohn | 2024/4/3 |
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection | arXiv preprint arXiv:2403.01472 | Anudeex Shetty Yue Teng Ke He Qiongkai Xu | 2024/3/3 |
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge | arXiv preprint arXiv:2402.19334 | Ansh Arora Xuanli He Maximilian Mozes Srinibas Swain Mark Dras | 2024/2/29 |
Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation | arXiv preprint arXiv:2402.16889 | Aditya Desu Xuanli He Qiongkai Xu Wei Lu | 2024/2/23 |
Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning | arXiv preprint arXiv:2404.19597 | Xuanli He Jun Wang Qiongkai Xu Pasquale Minervini Pontus Stenetorp | 2024/4/30 |
Attacks on Third-Party APIs of Large Language Models | arXiv preprint arXiv:2404.16891 | Wanru Zhao Vidit Khazanchi Haodi Xing Xuanli He Qiongkai Xu | 2024/4/24 |
Humanly Certifying Superhuman Classifiers | ICLR | Qiongkai Xu Christian Walder Chenchen Xu | 2023/5/1 |
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval | Findings of EMNLP | Fan Jiang Qiongkai Xu Tom Drummond Trevor Cohn | 2023/11/27 |
Training-free Lexical Backdoor Attacks on Language Models | Yujin Huang Terry Yue Zhuo Qiongkai Xu Han Hu Xingliang Yuan | 2023/4/30 | |
FLAT-Chat: A Word Recovery Attack on Federated Language Model Training | Qiongkai Xu Jun Wang Olga Ohrimenko Trevor Cohn | 2023/10/13 | |
Overview of the 2023 ALTA Shared Task: Discriminate between Human-Written and Machine-Generated Text | ALTA | Diego Molla Haolan Zhan Xuanli He Qiongkai Xu | 2023 |
Fingerprint Attack: Client De-Anonymization in Federated Learning | ECAI | Qiongkai Xu Trevor Cohn Olga Ohrimenko | 2023/9/12 |
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation | EMNLP | Xuanli He Qiongkai Xu Jun Wang Benjamin Rubinstein Trevor Cohn | 2023/5/19 |
Rethinking Round-Trip Translation for Machine Translation Evaluation | Findings of ACL | Terry Yue Zhuo Qiongkai Xu Xuanli He Trevor Cohn | 2023/5/2 |
Security Challenges in Natural Language Processing Models | Qiongkai Xu Xuanli He | 2023/12 | |
Privacy Protection in Conversations | Qiongkai Xu | 2022/8 | |
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation | arXiv preprint arXiv:2202.13363 | Zhuang Li Lizhen Qu Qiongkai Xu Tongtong Wu Tianyang Zhan | 2022/2/27 |
Protecting intellectual property of language generation apis with lexical watermark | AAAI | Xuanli He Qiongkai Xu Lingjuan Lyu Fangzhao Wu Chenguang Wang | 2022 |
Student Surpasses Teacher: Imitation attack for black-box nlp apis | arXiv preprint arXiv:2108.13873 | Qiongkai Xu Xuanli He Lingjuan Lyu Lizhen Qu Gholamreza Haffari | 2021/8/29 |
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks | NeurIPS | Xuanli He Qiongkai Xu Yi Zeng Lingjuan Lyu Fangzhao Wu | 2022/9/19 |
Co-Authors
