10 papers
GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG
Yang Gao, Gang Quan, Scott Piersall +3
Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, but existing pipelines typically operate on plaintext data, raising signifi…
R2-Router: A New Paradigm for LLM Routing with Reasoning
Jiaqi Xue, Qian Lou, Jiarong Xing +1
As LLMs proliferate with diverse capabilities and costs, LLM routing has emerged by learning to predict each LLM's quality and cost for a given query, then selecting the one with h…
Conjunctive Prompt Attacks in Multi-Agent LLM Systems
Nokimul Hasan Arif, Qian Lou, Mengxin Zheng
Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing crea…
Efficient Privacy-Preserving Sparse Matrix-Vector Multiplication Using Homomorphic Encryption
Yang Gao, Gang Quan, Wujie Wen +3
Sparse matrix-vector multiplication (SpMV) is a fundamental operation in scientific computing, data analysis, and machine learning. When the data being processed are sensitive, pre…
Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation
Tao Zhe, Huazhen Fang, Kunpeng Liu +3
Feature transformation enhances downstream task performance by generating informative features through mathematical feature crossing. Despite the advancements in deep learning, fea…
CryptoGen: Secure Transformer Generation with Encrypted KV-Cache Reuse
Hedong Zhang, Neusha Javidnia, Shweta Pardeshi +2
The widespread deployment of cloud-hosted generative models raises a fundamental challenge: enabling efficient autoregressive generation while preserving the privacy of both user p…