27 citations · 27 across the 5 of their papers we have counts for
7 papers
FedPix: Learning What to Share with Less Leakage in Federated Intelligence
Jingwei Zhao, Tiantong Sun, Yuanyuan Song +7
Existing federated intelligence paradigms primarily focus on how models are trained or aggregated, while overlooking a more fundamental question: \textbf{what information should le…
FUSE: Fairness-aware Update Screening against Byzantine Exploitation in -Fair Federated Learning
Tiantong Sun, Jinlin Liu, Xingru Wei +4
Client-level fair federated learning, in the form of -fair federated learning (-FFL), agnostic federated learning, or tilted empirical risk minimization, has emerged as an at…
A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
Zongru Li, Xingsheng Chen, Honggang Wen +8
Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and biological behavior. This sur…
Ten Challenging Problems in Federated Foundation Models
Tao Fan, Hanlin Gu, Xuemei Cao +30
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…
Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentives
Jiaqi Shao, Tao Lin, Xiaojin Zhang +2
Federated Unlearning (FU) enables the removal of specific clients' data influence from trained models. However, in non-IID settings, removing clients creates critical side effects:…
No Free Lunch Theorem for Privacy-Preserving LLM Inference
Xiaojin Zhang, Yahao Pang, Yan Kang +4
Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productiv…
Privacy in Large Language Models: Attacks, Defenses and Future Directions
Haoran Li, Yulin Chen, Jinglong Luo +9
The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipe…