Corpus Poisoning via Approximate Greedy Gradient Descent
Jinyan Su, Preslav Nakov, Claire Cardie.
MixUCB: Enhancing Safe Exploration in Contextual Bandits with Human Oversight
Jinyan Su, Jiankai Sun, Rohan Banerjee, Wen Sun, Sarah Dean.
Towards More Robust Retrieval-Augmented Generation:
Evaluating RAG Under Adversarial Poisoning Attacks
Jinyan Su, Jin peng Zhou, Zhengxin Zhang, Preslav Nakov, Claire Cardie.
Learning from Streaming Data when Users Choose
Jinyan Su, Sarah Dean
ICML 2024
M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection
Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohanned Afzal, Tarek Mahmoud, Giovanni Puccetti, Thomas Arnold, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov
ACL 2024
Adapting Fake News Detection to the Era of Large Language Models
Jinyan Su, Claire Cardie, Preslav Nakov
Findings of NAACL 2024
M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection.
Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Chenxi Whitehouse, Osama Mohammed Afzal, Tarek Mahmoud, Alham Fikri Aji, Preslav Nakov.
EACL 2024 (Resource paper award).
DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text
Jinyan Su, Terry Yue Zhuo, Di Wang, Preslav Nakov.
Findings of EMNLP 2023.
Leveraging large language models for structure learning in prompted weak supervision
Jinyan Su, Peilin Yu, Jieyu Zhang, Stephen H Bach.
IEEE BigData 2023
Differentially Private Stochastic Convex Optimization in (Non)-Euclidean Space Revisited
Jinyan Su, Changhong Zhao, Di Wang.
UAI 2023
Privacy Model with Public Unlabeled Data.
Jinyan Su, Jinhui Xu, Di Wang
ACML 2022 (Best paper award).
Faster Rates of Private Stochastic Convex Optimization
Jinyan Su, Lijie Hu, Di Wang,
ALT 2022