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

arXiv: https://arxiv.org/abs/2609.16742 · HTML: https://mlsanity.com/paper/2609.16742/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [A Systematic Literature Review on Hardware Reliability Assessment Methods for Deep Neural Networks](https://mlsanity.com/paper/2305.05750/) (2023)
- [FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks](https://mlsanity.com/paper/2003.12203/) (2020)
- [Edge AI: A Taxonomy, Systematic Review and Future Directions](https://mlsanity.com/paper/2407.04053/) (2024)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [ApproxABFT: Approximate Algorithm-Based Fault Tolerance for Neural Network Processing](https://mlsanity.com/paper/2302.10469/) (2023)

## Abstract (arXiv)

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 techniques that add minimal compute, memory, and latency overhead while integrating seamlessly with the standard GPU inference pipeline. Existing algorithm-based fault tolerance techniques rely on matrix augmentation and per-operation checksum verification, imposing substantial overhead that is prohibitive for CNN inference on embedded GPUs. In this work, we propose carry-through checksum, a fundamentally new scheme for soft-error detection in CNN inference on embedded GPUs. The method embeds dedicated carry-through filters into the convolutional layers, which compute a checksum from the CNN's own operations and propagate it through inference, enabling end-to-end error detection with a single output verification. Experimental results on multiple CNN architectures show that the proposed method detects 95.86% and 86.56% of critical faults for FP32 and FP16, respectively, at almost no additional per-image overhead. Detected faults are mitigated through re-execution, incurring only 2.27% run-time overhead across the entire test set on an NVIDIA Jetson Orin NX GPU.