Related papers: Flash: A Hybrid Private Inference Protocol for Dee…

Secure two-party computation with homomorphic encryption (HE) protects data privacy with a formal security guarantee but suffers from high communication overhead. While previous works, e.g., Cheetah, Iron, etc, have proposed efficient…

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…

Accelerating the deep learning inference is very important for real-time applications. In this paper, we propose a novel method to fuse the layers of convolutional neural networks (CNNs) on Graphics Processing Units (GPUs), which applies…

Real-time Deep Neural Network (DNN) inference with low-latency requirement has become increasingly important for numerous applications in both cloud computing (e.g., Apple's Siri) and edge computing (e.g., Google/Waymo's driverless car).…

Two-party computation (2PC) is promising to enable privacy-preserving deep learning (DL). However, the 2PC-based privacy-preserving DL implementation comes with high comparison protocol overhead from the non-linear operators. This work…

The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private inference is that…

Most existing secure neural network inference protocols based on secure multi-party computation (MPC) typically support at most four participants, demonstrating severely limited scalability. Liu et al. (USENIX Security'24) presented the…

Deep neural network (DNN) inference based on secure 2-party computation (2PC) can offer cryptographically-secure privacy protection but suffers from orders of magnitude latency overhead due to enormous communication. Previous works heavily…

The recently proposed Kolmogorov-Arnold Networks (KANs) offer enhanced interpretability and greater model expressiveness. However, KANs also present challenges related to privacy leakage during inference. Homomorphic encryption (HE)…

We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While multi-head mechanisms enhance expressivity in attention, naively…

Federated learning (FL) has come forward as a critical approach for privacy-preserving machine learning in healthcare, allowing collaborative model training across decentralized medical datasets without exchanging clients' data. However,…

Hardware specialization is becoming a key enabler of energyefficient performance. Future systems will be increasingly heterogeneous, integrating multiple specialized and programmable accelerators, each with different memory demands.…

The incessant advent of online services demands high speed and efficient recommender systems (ReS) that can maintain real-time performance along with processing very complex user-item interactions. The present study, therefore, considers…

It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular…

Convolutional neural networks (CNNs) have recently demonstrated superior quality for computational imaging applications. Therefore, they have great potential to revolutionize the image pipelines on cameras and displays. However, it is…

The gap between the cost of moving data and the cost of computing continues to grow, making it ever harder to design iterative solvers on extreme-scale architectures. This problem can be alleviated by alternative algorithms that reduce the…

Federated learning (FL) is a promising paradigm that enables collaboratively learning a shared model across massive clients while keeping the training data locally. However, for many existing FL systems, clients need to frequently exchange…

We evolve PyDTNN, a framework for distributed parallel training of Deep Neural Networks (DNNs), into an efficient inference tool for convolutional neural networks. Our optimization process on multicore ARM processors involves several…

Homomorphic Encryption (HE) is one of the most promising security solutions to emerging Machine Learning as a Service (MLaaS). Leveled-HE (LHE)-enabled Convolutional Neural Networks (LHECNNs) are proposed to implement MLaaS to avoid large…

Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been achieved by building deeper networks, posing a fundamental…