14 citations · 20 across the 9 of their papers we have counts for
9 papers
Module-Aware Parameter-Efficient Machine Unlearning on Transformers
Wenjie Bao, Jian Lou, Yuke Hu +5
Transformer has become fundamental to a vast series of pre-trained large models that have achieved remarkable success across diverse applications. Machine unlearning, which focuses…
Towards Evaluation for Real-World LLM Unlearning
Ke Miao, Yuke Hu, Xiaochen Li +4
This paper analyzes the limitations of existing unlearning evaluation metrics in terms of practicality, exactness, and robustness in real-world LLM unlearning scenarios. To overcom…
Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
Zhihao Liu, Jian Lou, Yuke Hu +6
Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request…
DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming
Shuya Feng, Meisam Mohammady, Han Wang +3
Streaming data, crucial for applications like crowdsourcing analytics, behavior studies, and real-time monitoring, faces significant privacy risks due to the large and diverse data…
Local Differentially Private Heavy Hitter Detection in Data Streams with Bounded Memory
Xiaochen Li, Weiran Liu, Jian Lou +4
Top- frequent items detection is a fundamental task in data stream mining. Many promising solutions are proposed to improve memory efficiency while still maintaining high accura…
Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding
Yuke Hu, Wei Liang, Ruofan Wu +5
Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging fe…
OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization
Xiaochen Li, Yuke Hu, Weiran Liu +5
Vertical Federated Learning (FL) is a new paradigm that enables users with non-overlapping attributes of the same data samples to jointly train a model without directly sharing the…
Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction
Xiaochen Li, Rui Zhong, Jian Liang +2
Rich user behavior information is of great importance for capturing and understanding user interest in click-through rate (CTR) prediction. To improve the richness, collecting long…
Privacy Enhancement via Dummy Points in the Shuffle Model
Xiaochen Li, Weiran Liu, Hanwen Feng +4
The shuffle model is recently proposed to address the issue of severe utility loss in Local Differential Privacy (LDP) due to distributed data randomization.In the shuffle model, a…