Related papers: EncFormer: Secure and Efficient Transformer Infere…
Machine learning (ML) systems that guarantee security and privacy often rely on Fully Homomorphic Encryption (FHE) as a cornerstone technique, enabling computations on encrypted data without exposing sensitive information. However, a…
With the increasing deployment of generative machine learning models in privacy-sensitive domains such as healthcare and personalized services, ensuring secure inference has become a critical challenge. Secure multi-party computation (MPC)…
Homomorphic encryption enables arbitrary computation over data while it remains encrypted. This privacy-preserving feature is attractive for machine learning, but requires significant computational time due to the large overhead of the…
Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoption of these primitives is the computational and communication…
Transformer models have gained significant attention due to their power in machine learning tasks. Their extensive deployment has raised concerns about the potential leakage of sensitive information during inference. However, when being…
Federated Learning (FL) enables collaborative model training across institutions without sharing raw data. However, gradient sharing still risks privacy leakage, such as gradient inversion attacks. Homomorphic Encryption (HE) can secure…
With the fast evolution of large language models (LLMs), privacy concerns with user queries arise as they may contain sensitive information. Private inference based on homomorphic encryption (HE) has been proposed to protect user query…
Due to the extensive application of machine learning (ML) in a wide range of fields and the necessity of data privacy, privacy-preserving machine learning (PPML) solutions have recently gained significant traction. One group of approaches…
We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data. Traditionally, addressing this challenge has involved…
The proliferation of machine learning services in the last few years has raised data privacy concerns. Homomorphic encryption (HE) enables inference using encrypted data but it incurs 100x-10,000x memory and runtime overheads. Secure deep…
Large Language Models (LLMs) are increasingly deployed on converged Cloud and High-Performance Computing (HPC) infrastructure. However, as LLMs handle confidential inputs and are fine-tuned on costly, proprietary datasets, their heightened…
Privacy-preserving neural network (NN) inference can be achieved by utilizing homomorphic encryption (HE), which allows computations to be directly carried out over ciphertexts. Popular HE schemes are built over large polynomial rings. To…
With the increasing awareness of privacy protection and data fragmentation problem, federated learning has been emerging as a new paradigm of machine learning. Federated learning tends to utilize various privacy preserving mechanisms to…
Fully Homomorphic Encryption (FHE) enables computation directly on encrypted data but incurs massive computational and memory overheads, often exceeding plaintext execution by several orders of magnitude. While custom ASIC accelerators can…
Collaborative machine learning across healthcare institutions promises improved diagnostic accuracy by leveraging diverse datasets, yet privacy regulations such as HIPAA prohibit direct patient data sharing. While federated learning (FL)…
The growing use of machine learning in cloud environments raises critical concerns about data security and privacy, especially in finance. Fully Homomorphic Encryption (FHE) offers a solution by enabling computations on encrypted data, but…
Two parties wish to collaborate on their datasets. However, before they reveal their datasets to each other, the parties want to have the guarantee that the collaboration would be fruitful. We look at this problem from the point of view of…
Publicly available large pretrained models (i.e., backbones) and lightweight adapters for parameter-efficient fine-tuning (PEFT) have become standard components in modern machine learning pipelines. However, preserving the privacy of both…
The classification service over a stream of data is becoming an important offering for cloud providers, but users may encounter obstacles in providing sensitive data due to privacy concerns. While Trusted Execution Environments (TEEs) are…
This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA Hopper GPUs for large language model (LLM) inference tasks. We benchmark the overhead introduced by TEE mode across various LLMs and…