Efficient Decoding Methods for Language Models on Encrypted Data

Large language models LLMs power modern AI applications, but processing sensitive data on untrusted servers raises privacy concerns. Homomorphic encryption HE enables computation on encrypted data for secure inference. However, neural text generation requires decoding methods like argmax and...

Enhancing Privacy in Decentralized Min-Max Optimization: a Differentially Private Approach

Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neighboring agents, eliminating the need for a central server. However, sharing model updates in such systems carry a ris...

Bridging Unsupervised and Semi-Supervised Anomaly Detection: a Theoretically-Grounded and Practical Framework with Synthetic Anomalies

Anomaly detection AD is a critical task across domains such as cybersecurity and healthcare. In the unsupervised setting, an effective and theoretically-grounded principle is to train classifiers to distinguish normal data from synthetic anomalies. We extend this principle to semi-supervised AD,...

GeoClip: Geometry-Aware Clipping for Differentially Private SGD

Differentially private stochastic gradient descent DP-SGD is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in DP-SGD is setting the per-sample gradient clipping threshold, which significantly affects the trade-off between privac...