MAED: Mathematical Activation Error Detection for Mitigating Physical Fault Attacks in DNN Inference

• URL: http://arxiv.org/abs/2603.18120v1
• Date: Wed, 18 Mar 2026 16:13:48 GMT
• Title: MAED: Mathematical Activation Error Detection for Mitigating Physical Fault Attacks in DNN Inference
• Abstract summary: This paper introduces MAED (Mathematical Activation Error Detection), an algorithm-level error detection framework.<n>It exploits mathematical identities to continuously validate the correctness of non-linear activation function computations at runtime.<n>It is the first to integrate algorithm-level error detection techniques to defend against both malicious fault injection attacks and naturally occurring faults in embedded systems.
• Score: 1.6624384368855523
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The inference phase of deep neural networks (DNNs) in embedded systems is increasingly vulnerable to fault attacks and failures, which can result in incorrect predictions. These vulnerabilities can potentially lead to catastrophic consequences, making the development of effective mitigation techniques essential. In this paper, we introduce MAED (Mathematical Activation Error Detection), an algorithm-level error detection framework that exploits mathematical identities to continuously validate the correctness of non-linear activation function computations at runtime. To the best of our knowledge, this work is the first to integrate algorithm-level error detection techniques to defend against both malicious fault injection attacks and naturally occurring faults in critical DNN components in embedded systems. The evaluation is conducted on three widely adopted activation functions, namely ReLu, sigmoid, and tanh which serve as fundamental building blocks for introducing non-linearity in DNNs and can lead to mispredictions when subjected to natural faults or fault attacks. We assessed the proposed error detection scheme via fault model simulation, achieving close to 100% error detection while mitigating existing fault attacks on DNN inference. Additionally, the overhead introduced by integrating the proposed scheme with the baseline implementation (i.e., without error detection) is validated through implementations on an AMD/Xilinx Artix-7 FPGA and an ATmega328P microcontroller, as well as through integration with TensorFlow. On the microcontroller, the proposed error detection incurs less than 1% clock cycle overhead, while on the FPGA it requires nearly zero additional area, at the cost of approximately a 20% increase in latency for sigmoid and tanh.

Related papers

• Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification [3.2623791881739033]
  We present DEFault -- a novel technique to detect and diagnose faults in Deep Neural Networks (DNN) programs.<n>Our approach achieves 94% recall in detecting real-world faulty DNN programs and 63% recall in diagnosing the root causes of the faults, demonstrating 3.92% - 11.54% higher performance than that of state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-01-22T00:55:09Z)
• BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks [65.666913051617]
  We introduce BDefects4NN, the first backdoor defect database for localization studies.<n>BDefects4NN provides labeled backdoor-defected DNNs at the neuron granularity and enables controlled localization studies of defect root causes.<n>We conduct experiments on evaluating six fault localization criteria and two defect repair techniques, which show limited effectiveness for backdoor defects.
  arXiv  Detail & Related papers  (2024-12-01T09:52:48Z)
• Efficient Algorithm Level Error Detection for Number-Theoretic Transform Assessed on FPGAs [2.156170153103442]
  This paper introduces algorithm level fault detection schemes in NTT multiplication. We evaluate this through the simulation of a fault model, ensuring that the conducted assessments accurately mirror the obtained results. We achieve a comparable throughput with just a 9% increase in area and 13% increase in latency compared to the original hardware implementations.
  arXiv  Detail & Related papers  (2024-03-02T14:05:56Z)
• ApproxABFT: Approximate Algorithm-Based Fault Tolerance for Neural Network Processing [7.578258600530223]
  Algorithm-based fault tolerance (ABFT) mechanisms have become a promising solution for reliability enhancement.<n>We propose an Approximate ABFT framework that introduces adaptive error tolerance thresholds to enable selective fault recovery.<n>The proposed ApproxABFT achieves a 43.39% average reduction in redundant computing overhead compared to previous accurate ABFT.
  arXiv  Detail & Related papers  (2023-02-21T06:21:28Z)
• Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators [6.8082132475259405]
  This paper focuses on quantifying the accuracy given that a transient error has occurred, which tells us how well a network behaves when a transient error occurs. We show that existing Resiliency Accuracy (RA) formulation is fundamentally inaccurate, because it incorrectly assumes that software variables have equal faulty probability under hardware transient faults. We present an algorithm that captures the faulty probabilities of DNN variables under transient faults and, thus, provides correct RA estimations validated by hardware.
  arXiv  Detail & Related papers  (2022-12-05T23:16:20Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• Fast and Accurate Error Simulation for CNNs against Soft Errors [64.54260986994163]
  We present a framework for the reliability analysis of Conal Neural Networks (CNNs) via an error simulation engine. These error models are defined based on the corruption patterns of the output of the CNN operators induced by faults. We show that our methodology achieves about 99% accuracy of the fault effects w.r.t. SASSIFI, and a speedup ranging from 44x up to 63x w.r.t.FI, that only implements a limited set of error models.
  arXiv  Detail & Related papers  (2022-06-04T19:45:02Z)
• Online Limited Memory Neural-Linear Bandits with Likelihood Matching [53.18698496031658]
  We study neural-linear bandits for solving problems where both exploration and representation learning play an important role. We propose a likelihood matching algorithm that is resilient to catastrophic forgetting and is completely online.
  arXiv  Detail & Related papers  (2021-02-07T14:19:07Z)
• Relaxing the Constraints on Predictive Coding Models [62.997667081978825]
  Predictive coding is an influential theory of cortical function which posits that the principal computation the brain performs is the minimization of prediction errors. Standard implementations of the algorithm still involve potentially neurally implausible features such as identical forward and backward weights, backward nonlinear derivatives, and 1-1 error unit connectivity. In this paper, we show that these features are not integral to the algorithm and can be removed either directly or through learning additional sets of parameters with Hebbian update rules without noticeable harm to learning performance.
  arXiv  Detail & Related papers  (2020-10-02T15:21:37Z)
• Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection [66.05992706105224]
  In this paper, an effective anomaly detection framework is proposed utilizing Bayesian Optimization technique. The performance of the considered algorithms is evaluated using the ISCX 2012 dataset. Experimental results show the effectiveness of the proposed framework in term of accuracy rate, precision, low-false alarm rate, and recall.
  arXiv  Detail & Related papers  (2020-08-05T19:29:35Z)
• FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks [13.100954947774163]
  Convolutional neural networks (CNNs) are becoming more and more important for solving challenging and critical problems in many fields. CNN inference applications have been deployed in safety-critical systems, which may suffer from soft errors caused by high-energy particles, high temperature, or abnormal voltage. Traditional fault tolerance methods are not suitable for CNN inference because error-correcting code is unable to protect computational components.
  arXiv  Detail & Related papers  (2020-03-27T02:01:54Z)
• Adaptive Anomaly Detection for IoT Data in Hierarchical Edge Computing [71.86955275376604]
  We propose an adaptive anomaly detection approach for hierarchical edge computing (HEC) systems to solve this problem. We design an adaptive scheme to select one of the models based on the contextual information extracted from input data, to perform anomaly detection. We evaluate our proposed approach using a real IoT dataset, and demonstrate that it reduces detection delay by 84% while maintaining almost the same accuracy as compared to offloading detection tasks to the cloud.
  arXiv  Detail & Related papers  (2020-01-10T05:29:17Z)

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.