Securing generative artificial intelligence with parallel magnetic tunnel junction true randomness

• URL: http://arxiv.org/abs/2510.01598v1
• Date: Thu, 02 Oct 2025 02:26:48 GMT
• Title: Securing generative artificial intelligence with parallel magnetic tunnel junction true randomness
• Authors: Youwei Bao, Shuhan Yang, Hyunsoo Yang,
• Abstract summary: generative artificial intelligence (GAI) models produce predictable patterns vulnerable to exploitation by attackers.<n>Here, we embed hardware-generated true random bits from spin-transfer torque magnetic tunnel junctions (STT-MTJs) to address the challenges.<n>A highly parallel, FPGA-assisted prototype computing system delivers megabit-per-second true random numbers.<n>Integrating the hardware random bits into a generative adversarial network (GAN) trained on CIFAR-10 reduces insecure outputs by up to 18.6 times compared to the low-quality random number generators (RNG) baseline.
• Score: 1.395525296189632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deterministic pseudo random number generators (PRNGs) used in generative artificial intelligence (GAI) models produce predictable patterns vulnerable to exploitation by attackers. Conventional defences against the vulnerabilities often come with significant energy and latency overhead. Here, we embed hardware-generated true random bits from spin-transfer torque magnetic tunnel junctions (STT-MTJs) to address the challenges. A highly parallel, FPGA-assisted prototype computing system delivers megabit-per-second true random numbers, passing NIST randomness tests after in-situ operations with minimal overhead. Integrating the hardware random bits into a generative adversarial network (GAN) trained on CIFAR-10 reduces insecure outputs by up to 18.6 times compared to the low-quality random number generators (RNG) baseline. With nanosecond switching speed, high energy efficiency, and established scalability, our STT-MTJ-based system holds the potential to scale beyond 106 parallel cells, achieving gigabit-per-second throughput suitable for large language model sampling. This advancement highlights spintronic RNGs as practical security components for next-generation GAI systems.

Related papers

• Semi-Device-Independent Quantum Random Number Generator Resistant to General Attacks [6.918556765582295]
  Quantum random number generators (QRNGs) produce true random numbers based on the inherent randomness of quantum theory.<n>In this paper, we propose a semi-DI QRNG that resists general attacks while accounting for finite-size effects.<n>Our work offers a promising approach to achieve both the robust security and high generation rate with a simple experimental setup.
  arXiv  Detail & Related papers  (2026-02-06T03:47:12Z)
• Adaptive Variation-Resilient Random Number Generator for Embedded Encryption [7.239794172995]
  We present an adaptive variation-resilient RNG capable of extracting unbiased encryption-grade random number streams from physically driven entropy sources.<n>The generated unbiased bit streams, due to their higher entropy, then only need to undergo simplified post-processing.
  arXiv  Detail & Related papers  (2025-07-07T22:42:49Z)
• DNN-Based Precoding in RIS-Aided mmWave MIMO Systems With Practical Phase Shift [43.56429251312585]
  This paper investigates maximizing the throughput of millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems with obstructed direct communication paths.<n>A reconfigurable intelligent surface (RIS) is employed to enhance transmissions, considering mmWave characteristics related to line-of-sight (LoS) and multipath effects.<n>Deep neural network (DNN) is developed to facilitate faster codeword selection.
  arXiv  Detail & Related papers  (2025-07-03T17:35:06Z)
• AI-Hybrid TRNG: Kernel-Based Deep Learning for Near-Uniform Entropy Harvesting from Physical Noise [0.0]
  AI-Hybrid TRNG is a deep-learning framework that extracts near-uniform entropy directly from physical noise.<n>It relies on a low-cost, thumb-sized RF front end, plus CPU-timing jitter, for training, and then emits 32-bit high-entropy streams without any quantization step.
  arXiv  Detail & Related papers  (2025-06-30T18:01:40Z)
• Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training [48.91359197313493]
  Zeroth-order (ZO) optimization is an emerging deep neural network (DNN) training paradigm that offers computational simplicity and memory savings.<n>ZO requires generating a substantial number of Gaussian random numbers, which poses significant difficulties and even makes it infeasible for hardware platforms, such as FPGAs and ASICs.<n>We propose PeZO, a perturbation-efficient ZO framework that significantly reduces the demand for random number generation.<n>Our experiments show that PeZO reduces the required LUTs and FFs for random number generation by 48.6% and 12.7%, and saves at maximum 86% power consumption
  arXiv  Detail & Related papers  (2025-04-28T23:58:07Z)
• Neuromorphic Wireless Split Computing with Multi-Level Spikes [69.73249913506042]
  Neuromorphic computing uses spiking neural networks (SNNs) to perform inference tasks.<n> embedding a small payload within each spike exchanged between spiking neurons can enhance inference accuracy without increasing energy consumption.<n> split computing - where an SNN is partitioned across two devices - is a promising solution.<n>This paper presents the first comprehensive study of a neuromorphic wireless split computing architecture that employs multi-level SNNs.
  arXiv  Detail & Related papers  (2024-11-07T14:08:35Z)
• Neuromorphic Split Computing with Wake-Up Radios: Architecture and Design via Digital Twinning [97.99077847606624]
  This work proposes a novel architecture that integrates a wake-up radio mechanism within a split computing system consisting of remote, wirelessly connected, NPUs. A key challenge in the design of a wake-up radio-based neuromorphic split computing system is the selection of thresholds for sensing, wake-up signal detection, and decision making.
  arXiv  Detail & Related papers  (2024-04-02T10:19:04Z)
• Parallel and real-time post-processing for quantum random number generators [5.864108266054829]
  This work explores the parallel and real-time implementation of multiple seed real-time updating toeplitz hash extractors in an FPGA to achieve parallel QRNGs. With the use of higher-performance ADCs, we attained a random number production rate exceeding 20Gbps. This marks a significant step toward chip-based parallel QRNGs, enhancing the practicality of CV QRNGs in trusted, device-independent, and semi-device-independent scenarios.
  arXiv  Detail & Related papers  (2024-03-28T15:05:39Z)
• LL-GNN: Low Latency Graph Neural Networks on FPGAs for High Energy Physics [45.666822327616046]
  This work presents a novel reconfigurable architecture for Low Graph Neural Network (LL-GNN) designs for particle detectors. The LL-GNN design advances the next generation of trigger systems by enabling sophisticated algorithms to process experimental data efficiently.
  arXiv  Detail & Related papers  (2022-09-28T12:55:35Z)
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition [62.83832841523525]
  We propose a fast and accurate parallel transformer, termed Paraformer. It accurately predicts the number of output tokens and extract hidden variables. It can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.
  arXiv  Detail & Related papers  (2022-06-16T17:24:14Z)
• Deep Transformer Networks for Time Series Classification: The NPP Safety Case [59.20947681019466]
  An advanced temporal neural network referred to as the Transformer is used within a supervised learning fashion to model the time-dependent NPP simulation data. The Transformer can learn the characteristics of the sequential data and yield promising performance with approximately 99% classification accuracy on the testing dataset.
  arXiv  Detail & Related papers  (2021-04-09T14:26:25Z)
• Scalable quantum random number generator for cryptography based on the random flip-flop approach [1.2578844450585998]
  We present a quantum random number generator (QRNG) which makes use of a photoelectric effect in single-photon avalanche diodes (SPADs) as a source of randomness. For the first time we investigate this method in detail and find that, out of two main imperfections, bias is due only to hardware imperfections.
  arXiv  Detail & Related papers  (2021-02-24T11:00:22Z)
• A High Speed Integrated Quantum Random Number Generator with on-Chip Real-Time Randomness Extraction [2.759846687681801]
  We present the first integrated Quantum RNG (QRNG) in a standard CMOS technology node. We show that co-integration of combinational logic, even of high complexity, does not affect the quality of randomness. Our CMOS QRNG can reach up to 400 Mbit/s throughput with low power consumption.
  arXiv  Detail & Related papers  (2021-02-11T19:55:29Z)
• EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference [82.1584439276834]
  Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. We present EdgeBERT, an in-depth algorithm- hardware co-design for latency-aware energy optimization for multi-task NLP.
  arXiv  Detail & Related papers  (2020-11-28T19:21:47Z)

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.