EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer
Not on the map. Why?
Abstract (arXiv)
True Random Number Generators (TRNGs) play a fundamental role in hardware security, cryptographic systems, and data protection. In the context of Deep NeuralNetworks (DNNs), safeguarding model parameters, particularly weights, is critical to ensure the integrity, privacy, and intel-lectual property of AI systems. While software-based pseudo-random number generators are widely used, they lack the unpredictability and resilience offered by hardware-based TRNGs. In this work, we propose a novel and robust Encoding-in-Memory TRNG called EIM-TRNG that leverages the inherent physical randomness in DRAM cell behavior, particularly under RowHammer-induced disturbances, for the first time. We demonstrate how the unpredictable bit-flips generated through carefully controlled RowHammer operations can be harnessed as a reliable entropy source. Furthermore, we apply this TRNG framework to secure DNN weight data by encoding via a combination of fixed and unpredictable bit-flips. The encrypted data is later decrypted using a key derived from the probabilistic flip behavior, ensuring both data confidentiality and model authenticity. Our results validate the effectiveness of DRAM-based entropy extraction for robust, low-cost hardware security and offer a promising direction for protecting machine learning models at the hardware level.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 47 references that are in the map. First posted on arXiv 3 Jul 2025.
Builds on
18 of 47 references.
References · 18
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2021DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memoriescited by 42
- 2019EDEN: Enabling Energy-Efficient, High-Performance Deep Neural Network Inference Using Approximate DRAMcited by 24
- 2020TRRespass: Exploiting the Many Sides of Target Row Refreshcited by 11
- 2023MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inferencecited by 9
- 2021QUAC-TRNG: High-Throughput True Random Number Generation Using Quadruple Row Activation in Commodity DRAM Chipscited by 7
- 2021Uncovering In-DRAM RowHammer Protection Mechanisms: A New Methodology, Custom RowHammer Patterns, and Implicationscited by 7
- 2018D-RaNGe: Using Commodity DRAM Devices to Generate True Random Numbers with Low Latency and High Throughputcited by 6
- 2022DR-STRaNGe: End-to-End System Design for DRAM-based True Random Number Generatorscited by 3
- 2022DRAM Bender: An Extensible and Versatile FPGA-based Infrastructure to Easily Test State-of-the-art DRAM Chipscited by 3
- 2023DNN-Defender: A Victim-Focused In-DRAM Defense Mechanism for Taming Adversarial Weight Attack on DNNscited by 2
- 2023DRAM-Locker: A General-Purpose DRAM Protection Mechanism against Adversarial DNN Weight Attackscited by 2
6 more
- 2024TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environmentscited by 2
- 2018Exploiting DRAM Latency Variations for Generating True Random Numberscited by 1
- 2023Threshold Breaker: Can Counter-Based RowHammer Prevention Mechanisms Truly Safeguard DRAM?cited by 1
- 2024Compromising the Intelligence of Modern DNNs: On the Effectiveness of Targeted RowPresscited by 1
- 2025Understanding RowHammer Under Reduced Refresh Latency: Experimental Analysis of Real DRAM Chips and Implications on Future Solutionscited by 1
- 2025Chronus: Understanding and Securing the Cutting-Edge Industry Solutions to DRAM Read Disturbancecited by 1
Built on by
Not cited yet.