Radiation Effects in Electronics

Latest papers

• Reliability Theory for AI Control

  Grant Molnar · 23 September 2026

  Reliability theory gives a mature language for layered systems, but its formal tools are not yet standard in frontier AI control. We apply them to Google DeepMind's defenses against rogue deployment. The same control stack can have cubic, quadratic, or linear rare-failure suppression depending on it…

• Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication

  Yafan Huang, Guanpeng Li · 18 September 2026

  We propose PaRID (PaRallel Instruction Duplication), a software-directed soft error detection framework that requires only compile-time effort for multithreading parallel programs. PaRID addresses two key challenges: supporting parallel programs with mixed serial and parallel regions and minimizing …

• WARD: Runtime Workload-Adaptive Vision TRansformer Framework for Dependable Edge AI

  Mahdi Taheri, Pramit Kumar Bhaduri, Mohammad Masoumi, Ali Mahani · 17 September 2026

  Edge-deployed AI operate under dynamically changing power budgets, reliability requirements, and input distributions, requiring continuous adaptation. Such conditions arise in long-running edge AI applications, including autonomous systems, industrial monitoring, and satellite onboard intelligence. …

• REQAP: Resilient Weight Packing and Quantization for Edge DNN Acceleration

  Mahdi Taheri, Samira Nazari, Mubassher Ansari, Ali Azarpeyvand, Mohsen Afsharchi, Maksim Jenihhin, Christian Herglotz · 17 September 2026

  Efficient deployment of Deep Neural Networks (DNNs) on edge accelerators requires aggressive model compression while maintaining reliability in fault-prone hardware environments. This paper presents a reliability-aware quantized weight packing methodology for systolic-array-based DNN accelerators. A…

• Carry-Through Checksum: A Lightweight Fault-Detection for CNN Inference at the Edge

  Kyrylo Nazarevych, Mohammad Hasan Ahmadilivani, Krister Kaldre, Davide Bertozzi, Jaan Raik · 16 September 2026

  Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference outputs and lead to unsafe decisions. Such applications typically rely on resource-constrained embedded GPUs, requiring fault detection and mitigation…

• Proton Irradiation Characterization of an Open-Source ML Accelerator on a Zynq UltraScale+ MPSoC

  Saad Memon, Rafal Graczyk, Jan Swako\'n, Leszek Grzanka, Sebastian Kusyk, Mike Papadakis · 7 September 2026

  As spaceborne computing systems increasingly rely on neural network (NN) accelerators, the opacity of commercial, black-box architectures severely restricts the development of verifiable radiation mitigation strategies. Open-source, register-transfer level (RTL)-accessible accelerators resolve this …

• TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks

  Noam Bires, Marcello Traiola, Angeliki Kritikakou, Elisa Fromont · 7 September 2026

  Reliability evaluation of deep neural networks under hardware faults commonly relies on fault injection, but exhaustive campaigns are intractable for modern models and datasets. Statistical fault injection reduces this cost, yet existing approaches still require large injection budgets because they …

• RACE-AIMC: Selective Inference for Heterogeneous Analog In-Memory Accelerators at the Edge

  Osama Yousuf, Martin Lueker-Boden · 4 September 2026

  Analog in-memory computing (AIMC) speeds up neural-network inference by doing the arithmetic directly inside a memory array, instead of shuttling weights back and forth between memory and a processor. This saves energy, but the physical devices that store the weights are imperfect: programming error…

• Adaptive Sequential Test Planning for Multi-Mechanism Reliability Qualification via Bayesian Monte Carlo Tree Search

  Youssef A. Elhagrasy, Ian Hill, Andr\'e Ivanov · 11 August 2026

  Reliability qualification of advanced semiconductor devices requires sequential stress decisions that balance characterization objectives against multiple competing failure mechanisms. Current practice relies on static test plans derived from population-level acceleration models, which cannot adapt …

• Understanding Fault Tolerance of Adversarially Robust Pruned Models

  Manali Dangarikar, Cory Merkel · 6 August 2026

  Deep neural networks (DNNs) deployed on resource-constrained neuromorphic hardware face three concurrent challenges: the need for model compression through pruning, vulnerability to adversarial input perturbations, and susceptibility to hardware-induced weight faults such as stuck-at-zero errors. Wh…

• CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers

  Mohammad Hasan Ahmadilivani, Sven-Markus Loorits, Jaan Raik · 6 August 2026

  The wide adoption of Vision Transformers (ViTs) in safety-critical applications raises reliability concerns related to hardware faults. Algorithm-Based Fault Tolerance (ABFT) methods have emerged as lightweight and symmetric protection mechanisms for DNNs. However, they are particularly challenging …

• Evaluating Forecasting Techniques for Hardware Errors on a Large-scale HPC System

  Kaiyuan Liao, Xiwei Xuan, Tanwi Mallick, Kevin Brown, Christopher D. Carothers, Kwan-Liu Ma · 4 August 2026

  Hardware error logs in high-performance computing (HPC) systems provide early signals of abnormal behavior, yet there remain challenges in effectively forecasting these errors using modern predictive methods. This work investigates the boundaries of applying time series forecasting to HPC hardware e…

• From Bit-Position Sensitivity to Unequal Error Protection for DNN Inference Memory

  Muhammad Husnain Mubarik, Karthik Mohan Kumar, Pedro Antonio Pena, Keshavan Varadarajan, Kunal Tyagi · 23 July 2026

  We characterize per-bit-position fault sensitivity in ML inference across 16 workloads -- spanning transformer-based models and attention-free CNNs -- and across three floating-point formats. Our central empirical finding is a sharp bit-sensitivity transition: flipping any of the least-significant f…

• CoG-Guided Weight Correction for Fault-Tolerant Deep Neural Networks

  Bahram Parchekani, Samira Nazari, Ali Azarpeyvand, Mohammad Hasan Ahmadilivani, Tara Ghasempouri, Jaan Raik · 20 July 2026

  Deep Neural Networks (DNNs) used in safety-critical applications are vulnerable to hardware and memory faults that corrupt network weights and degrade reliability. In this paper, we propose a Center of Gravity (CoG) guided weight correction method that restores faulty weights based on their spatial …

• Real-Time Detection of Charge Jumps in Superconducting Qubits with a Convolutional Neural Network

  Daniel Gaytan-Villarreal, Peter Meiring, Daniel Baxter, Daniel Bowring, Grace Bratrud, Matteo Cremonesi, Giuseppe Di Guglielmo, Grace Wagner, Bowen Xiao · 17 July 2026

  Ionizing radiation from cosmic rays and gammas can induce discontinuous jumps in the environmental charge of superconducting qubits (charge jumps), causing correlated errors that challenge fault-tolerant quantum computing while simultaneously providing a detection signature for quantum sensing appli…

• Emulated Integrity Replica: Enabling Self-Healing on FPGA SoCs via Hierarchical Twins

  Arsalan Ali Malik, Ali Suvizi, Guru Venkataramani, Aydin Aysu · 15 July 2026

  Convolutional neural networks (CNNs) are increasingly being deployed on system-on-chip (SoC) platforms, where hardware-accelerated inference enables low-latency edge computing. Achieving fault tolerance on these devices remains challenging because conventional redundancy (dual/triple modular redunda…

• QANTIS: Hardware-Calibrated Sequential POMDP Belief Updates on IBM Heron

  Bayram Yuksel Eker, Suayb S. Arslan, Ozgur Nazli, Mustafa Serhat Demirgil, Furkan Deligoz · 9 July 2026

  Autonomous systems under partial observability act on beliefs, not raw sensor events. QANTIS treats the quantum processor as a calibrated belief-update service in that loop: it receives a prior and an observation model, estimates the rare-event evidence term, and returns an ordinary posterior to a c…

• ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators

  Xinxin Chen, Haoran Qiao, Yiming Guo, Kecheng Luo, Siyuan Feng, Jingwen Ma · 3 July 2026

  SRAM-based FPGAs provide an attractive platform for energy- and latency-constrained CNN inference at the network edge, yet transient faults can lead to silent errors that compromise reliability. Always-on redundancy (e.g., full TMR) improves correctness but incurs substantial performance and energy …

• SENTRY: Statistical Reliability Analysis of Vision Transformers Under Soft Errors

  Pramit Kumar Bhaduri, Mahdi Taheri, Samira Nazari, Maksim Jenihhin, Christian Herglotz, Michael Hubner · 9 June 2026

  With the growth of Vision Transformers in safety-critical domains like autonomous systems and medical imaging, ensuring their reliability against soft errors is paramount. While ViTs offer state-of-the-art accuracy, their massive parameter counts render exhaustive fault injection campaigns infeasibl…

• AI from concrete to abstract: demystifying artificial intelligence to the general public

  Rubens Lacerda Queiroz, F\'abio Ferrentini Sampaio, Cabral Lima, Priscila Machado Vieira Lima · 4 June 2026

  Artificial Intelligence (AI) has been adopted in a wide range of domains. This shows the imperative need to develop means to endow common people with a minimum understanding of what AI means. Combining visual programming and WiSARD weightless artificial neural networks, this article presents a new m…

• Lightweight CNN-Based Anomaly Detection for High Voltage Converter Modulators in the Spallation Neutron Source

  Alberto D. Cencillo, Leonardo Concepci\'on, Juli\'an Luengo, Isaac Triguero · 1 June 2026

  Unscheduled trips of high-power pulsed converters are a leading source of downtime at large accelerator facilities. At the Spallation Neutron Source (SNS), the High Voltage Converter Modulators (HVCMs) are consistently the second-largest contributor to lost beam time. Each HVCM pulse is recorded acr…

• Effective and Memory-Efficient Alternatives to ECC for Reliable Large-Scale DNNs

  Mohammad Hasan Ahmadilivani, Marten Roots, Marco Restifo, Sven-Markus Loorits, Luca Di Mauro, Jaan Raik · 11 May 2026

  Modern Deep Learning (DL) workloads are increasingly deployed in safety-critical domains, such as automotive systems and hyperscale data centers, where transient hardware faults pose a serious threat to system reliability. These workloads are highly memory-intensive, and their correct functionality …

• Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates

  Pawel Kaplanski (Kaplanski AI Lab) · 5 May 2026

  Recursive language-model loops often settle into recognizable attractor-like patterns. The practical question is how much injected text is needed to move a settled loop somewhere else, and whether that move lasts. We study this in 30-step recursive loops by separating the model from the context-upda…

• Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)

  Taibiao Zhao, Xiang Zhang, Mingxuan Sun, Ruyi Ding, Xugui Zhou · 14 April 2026

  Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips caused by cosmic radiation or low-voltage operation may corrupt DNN computations, distort driving decisions, and lead to…

• Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems

  Taibiao Zhao, Xiang Zhang, Mingxuan Sun, Ruyi Ding, Xugui Zhou · 7 April 2026

  Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM during inference, bit flips caused by cosmic radiation or low-voltage operation may corrupt DNN computations, distort driving decisions, and lead to…