Scholar
Qiongkai Xu
Google Scholar ID: wCer2WUAAAAJ
Lecturer (Asst. Prof.) @ Macquarie University
Citations & Impact
Citations
3,599
H-index
17
i10-index
25
Publications
20
Co-authors
18
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - “IDT: Dual-Task Adversarial Attacks for Privacy Protection” accepted by Computational Linguistics (CL)
- - “Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation” accepted by Transactions on Machine Learning Research (TMLR)
- - Four papers accepted to EMNLP 2025
- - Three papers accepted to ACL 2025
- - One demo paper accepted to WWW 2025
- - “Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients” accepted to EMNLP 2024
- - “SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks” accepted by TACL
- - “Backdoor Attacks on Multilingual Machine Translation” accepted to NAACL
- - Awards:
- - Won Macquarie University Research Pitching Session twice
- - Students awarded CIS PhD scholarship and DFCRC scholarship
- - Projects:
- - Anti-BAD competition supported by Google Cloud Research Credits Program
- - Seed grant from Macquarie University Incubator
Research Experience
- - Lecturer at Macquarie University
- - Honorary Fellow at University of Melbourne
- - Former Research Fellow at University of Melbourne
Education
- - Ph.D. from Australian National University
- - Advisor Information: Not provided
Background
- - Research Interests: Natural Language Processing, Privacy & Security, Machine Learning and Data Mining
- - Professional Field: Auditing machine learning models, specifically 1) identifying and addressing privacy and security issues in ML/NLP models and their applications; 2) developing comprehensive evaluation theory and methods for ML/NLP models from various perspectives
