Publications (21)
Fox-1: Open Small Language Model for Cloud and Edge
Zijian Hu, Jipeng Zhang, Rui Pan +9
We present Fox-1, a series of small language models (SLMs) consisting of Fox-1-1.6B and Fox-1-1.6B-Instruct-v0.1. These models are pre-trained on 3 trillion tokens of web-scraped d…
FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System
Weizhao Jin, Yuhang Yao, Shanshan Han +5
Federated Learning trains machine learning models on distributed devices by aggregating local model updates instead of local data. However, privacy concerns arise as the aggregated…
FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
Shanshan Han, Baturalp Buyukates, Zijian Hu +13
This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defens…
Don't Stir the Pot! Authorized Vector Data Retrieval via Access-Aware Indexing
Shanshan Han, Vishal Chakraborty, Sharad Mehrotra
Vector databases increasingly enforce role-based access control, where each top-k approximate nearest neighbor query must return only vectors the querying role is authorized to acc…
Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data
Jiaqi Shao, Shanshan Han, Chaoyang He +1
Federated heavy-hitter analytics involves the identification of the most frequent items within distributed data. Existing methods for this task often encounter challenges such as c…
Hiding Access-pattern is Not Enough! Veil: A Storage and Communication Efficient Volume-Hiding Algorithm
Shanshan Han, Vishal Chakraborty, Michael Goodrich +2
This paper addresses volume leakage (i.e., leakage of the number of records in the answer set) when processing keyword queries in encrypted key-value (KV) datasets. Volume leakage,…