RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning

• URL: http://arxiv.org/abs/2607.18169v1
• Date: Mon, 20 Jul 2026 17:11:59 GMT
• Title: RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning
• Abstract summary: Resistive-switching random-access memory (RRAM) is an attractive substrate for efficient Edge Artificial Intelligence of Things (AIoT)<n>We propose RRAM-DP, a hardware-algorithm co-design that relaxes RRAM write-verify operations to inject calibrated noise for inherently (epsilon, delta)-DP with formal DP analysis.<n>At the same privacy level, RRAM-DP-SGD delivers up to 57x and 3.2x energy savings and 2.7x and 1.8x speedups over A100 and DiVaGEMM, respectively.
• Score: 21.69171006139815
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Edge Artificial Intelligence of Things (AIoT) systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory (RRAM) is an attractive substrate for efficient AIoT thanks to its multi-bit storage and compute-in-memory (CiM) capabilities, while its inherently stochastic write behavior provides a natural source of randomness that can be leveraged for differential privacy (DP) protection. Yet how to transform this device-level randomness-typically viewed as detrimental to accuracy-into a principled randomized mechanism while preserving model utility remains underexplored. We propose RRAM-DP, a hardware-algorithm co-design that relaxes RRAM write-verify operations to inject calibrated noise for inherently (epsilon, delta)-DP with formal DP analysis; together with pretraining techniques, it renders a novel private, high-utility CiM training paradigm. On CIFAR-10/100, STS-B, and SST-2, RRAM-DP-SGD incurs at best only a 3.8% accuracy drop at (epsilon=2, delta=O(1/n))-DP relative to non-private SGD. At the same privacy level, RRAM-DP-SGD delivers up to 57x and 3.2x energy savings and 2.7x and 1.8x speedups over A100 and DiVa-GEMM, respectively. These results point toward efficient, privacy-preserving in-memory training on RRAM at the edge.

Related papers

• SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning [0.0]
  Differentially private gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise.<n>We propose textbfSMA-DPSGD, a textbfSpectral MemoryAware method that augments DP-SGD with a fractional memory branch.<n>Experiments on CIFAR-100, CIFAR-10, and MNIST show competitive or superior accuracy over several DP optimization baselines.
  arXiv  Detail & Related papers  (2026-05-19T20:02:19Z)
• RPWithPrior: Label Differential Privacy in Regression [0.0]
  In this paper, we focus on regression tasks under $$-label differential privacy guarantees.<n>We model both original and randomized responses as continuous random variables, avoiding discretization entirely.<n>We prove that our algorithm, RPWithPrior, guarantees $$-label differential privacy.
  arXiv  Detail & Related papers  (2026-01-30T06:27:13Z)
• CNN-Based Automated Parameter Extraction Framework for Modeling Memristive Devices [0.0]
  Resistive random access memory (RRAM) is a promising candidate for next-generation nonvolatile memory (NVM) and in-memory computing applications.<n> Compact models are essential for analyzing the circuit and system-level performance of experimental RRAM devices.<n>This work presents an automated framework for extracting the fitting parameters of the widely used Stanford RRAM model directly from device I-V characteristics.
  arXiv  Detail & Related papers  (2025-11-11T07:24:39Z)
• Machine Learning with Privacy for Protected Attributes [56.44253915927481]
  We refine the definition of differential privacy (DP) to create a more general and flexible framework that we call feature differential privacy (FDP)<n>Our definition is simulation-based and allows for both addition/removal and replacement variants of privacy, and can handle arbitrary separation of protected and non-protected features.<n>We apply our framework to various machine learning tasks and show that it can significantly improve the utility of DP-trained models when public features are available.
  arXiv  Detail & Related papers  (2025-06-24T17:53:28Z)
• Two Birds with One Stone: Differential Privacy by Low-power SRAM Memory [3.574643703197513]
  We develop a hardware-based technique to achieve differential privacy by design. Our design realizes local differential privacy (LDP) by harnessing the inherent hardware noise into controlled LDP noise when data is stored in the memory. The results confirm that the developed technique is differentially private, saves 88.58% system power, speeds up software-based DP mechanisms by more than 106 times, while only incurring 2.46% chip overhead and 7.81% estimation errors in data recovery.
  arXiv  Detail & Related papers  (2024-03-26T01:14:55Z)
• Private Fine-tuning of Large Language Models with Zeroth-order Optimization [51.19403058739522]
  Differentially private gradient descent (DP-SGD) allows models to be trained in a privacy-preserving manner.<n>We introduce DP-ZO, a private fine-tuning framework for large language models by privatizing zeroth order optimization methods.
  arXiv  Detail & Related papers  (2024-01-09T03:53:59Z)
• Pruning random resistive memory for optimizing analogue AI [54.21621702814583]
  AI models present unprecedented challenges to energy consumption and environmental sustainability. One promising solution is to revisit analogue computing, a technique that predates digital computing. Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning.
  arXiv  Detail & Related papers  (2023-11-13T08:59:01Z)
• DDC-PIM: Efficient Algorithm/Architecture Co-design for Doubling Data Capacity of SRAM-based Processing-In-Memory [6.367916611208411]
  We propose DDC-PIM, an efficient algorithm/architecture co-design methodology that effectively doubles the equivalent data capacity. DDC-PIM yields about $2.84times$ speedup on MobileNetV2 and $2.69times$ on EfficientNet-B0 with negligible accuracy loss. Compared with state-of-the-art macros, DDC-PIM achieves up to $8.41times$ and $2.75times$ improvement in weight density and area efficiency, respectively.
  arXiv  Detail & Related papers  (2023-10-31T12:49:54Z)
• DPZero: Private Fine-Tuning of Language Models without Backpropagation [49.365749361283704]
  We introduce DPZero, a novel private zeroth-order algorithm with nearly dimension-independent rates. The memory efficiency of DPZero is demonstrated in privately fine-tuning RoBERTa and OPT on several downstream tasks.
  arXiv  Detail & Related papers  (2023-10-14T18:42:56Z)
• DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass [22.578388829171157]
  DP-Forward perturbs embedding in the forward pass of language models. It almost hits the non-private baseline and outperforms DP-SGD by up to 7.7pp at a moderate privacy level.
  arXiv  Detail & Related papers  (2023-09-13T06:37:53Z)
• Self-Gated Memory Recurrent Network for Efficient Scalable HDR Deghosting [59.04604001936661]
  We propose a novel recurrent network-based HDR deghosting method for fusing arbitrary length dynamic sequences. We introduce a new recurrent cell architecture, namely Self-Gated Memory (SGM) cell, that outperforms the standard LSTM cell. The proposed approach achieves state-of-the-art performance compared to existing HDR deghosting methods quantitatively across three publicly available datasets.
  arXiv  Detail & Related papers  (2021-12-24T12:36:33Z)
• SreaMRAK a Streaming Multi-Resolution Adaptive Kernel Algorithm [60.61943386819384]
  Existing implementations of KRR require that all the data is stored in the main memory. We propose StreaMRAK - a streaming version of KRR. We present a showcase study on two synthetic problems and the prediction of the trajectory of a double pendulum.
  arXiv  Detail & Related papers  (2021-08-23T21:03:09Z)
• Lossless Compression of Efficient Private Local Randomizers [55.657133416044104]
  Locally Differentially Private (LDP) Reports are commonly used for collection of statistics and machine learning in the federated setting. In many cases the best known LDP algorithms require sending prohibitively large messages from the client device to the server. This has led to significant efforts on reducing the communication cost of LDP algorithms.
  arXiv  Detail & Related papers  (2021-02-24T07:04:30Z)
• A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework [56.57225686288006]
  Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. Previous pruning methods mainly focus on reducing the model size and/or improving performance without considering the privacy of user data. We propose a privacy-preserving-oriented pruning and mobile acceleration framework that does not require the private training dataset.
  arXiv  Detail & Related papers  (2020-03-13T23:52:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.