Related papers: SIMC 2.0: Improved Secure ML Inference Against Mal…
Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obfuscated malicious intent during inference and refuse…
Mobile collaborative learning (MCL) is highly acknowledged and focusing paradigm in eductional institutions and several organizations across the world. It exhibits intellectual synergy of various combined minds to handle the problem and…
In this paper, we address the problem of privacy-preserving federated neural network training with $N$ users. We present Hercules, an efficient and high-precision training framework that can tolerate collusion of up to $N-1$ users. Hercules…
Oblivious inference is the task of outsourcing a ML model, like neural-networks, without disclosing critical and sensitive information, like the model's parameters. One of the most prominent solutions for secure oblivious inference is based…
Security-Constrained Unit Commitment (SCUC) is a fundamental problem in power systems and electricity markets. In practical settings, SCUC is repeatedly solved via Mixed-Integer Linear Programming, sometimes multiple times per day, with…
This paper focuses on designing a privacy-preserving Machine Learning (ML) inference protocol for a hierarchical setup, where clients own/generate data, model owners (cloud servers) have a pre-trained ML model, and edge servers perform ML…
Federated Learning (FL) enables collaborative model training without centralizing client data, making it attractive for privacy-sensitive domains. While existing approaches employ cryptographic techniques such as homomorphic encryption,…
The concrete efficiency of secure computation has been the focus of many recent works. In this work, we present concretely-efficient protocols for secure $3$-party computation (3PC) over a ring of integers modulo $2^{\ell}$ tolerating one…
The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…
Many ML applications and products train on medium amounts of input data but get bottlenecked in real-time inference. When implementing ML systems, conventional wisdom favors segregating ML code into services queried by product code via…
Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…
We describe scalable protocols for solving the secure multi-party computation (MPC) problem among a large number of parties. We consider both the synchronous and the asynchronous communication models. In the synchronous setting, our…
Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…
We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that can be verbatim extracted from context. CopySpec identifies…
Due to the great development of secure multi-party computation, many practical secure computation schemes have been proposed. As an example, different secure auction mechanisms have been widely studied, which can protect bid privacy while…
Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process client inputs without decrypting them. Although prior…
As machine learning (ML) models become increasingly deployed through cloud infrastructures, the confidentiality of user data during inference poses a significant security challenge. Homomorphic Encryption (HE) has emerged as a compelling…
Collaborative machine learning (CML) enables multiple clients to train a global model jointly in a data-distributed setting. To address data privacy and communication efficiency, one-shot CML has been increasingly adopted, where clients…
This paper introduces LLMServingSim2.0, a system simulator designed for exploring heterogeneous hardware in large-scale LLM serving systems. LLMServingSim2.0 addresses two key limitations of its predecessor: (1) integrating hardware models…
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…