# A Low-cost Strategic Monitoring Approach for Scalable and Interpretable Error Detection in Deep Neural Networks

arXiv: https://arxiv.org/abs/2310.20349 · HTML: https://mlsanity.com/paper/2310.20349/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 14 of 14)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [On Detecting Adversarial Perturbations](https://mlsanity.com/paper/1702.04267/) (2017)
- [Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks](https://mlsanity.com/paper/1906.01017/) (2019)
- [Outside the Box: Abstraction-Based Monitoring of Neural Networks](https://mlsanity.com/paper/1911.09032/) (2019)
- [Runtime Monitoring Neuron Activation Patterns](https://mlsanity.com/paper/1809.06573/) (2018)
- [FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation](https://mlsanity.com/paper/1912.00941/) (2019)
- [Object Detection in Autonomous Vehicles: Status and Open Challenges](https://mlsanity.com/paper/2201.07706/) (2022)
- [Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision](https://mlsanity.com/paper/2108.07019/) (2021)
- [Hardware faults that matter: Understanding and Estimating the safety impact of hardware faults on object detection DNNs](https://mlsanity.com/paper/2209.03225/) (2022)
- [A Uniform Framework for Anomaly Detection in Deep Neural Networks](https://mlsanity.com/paper/2110.03092/) (2021)

## Built on by (most cited first, 6 of 6)

- [A Flow-based Credibility Metric for Safety-critical Pedestrian Detection](https://mlsanity.com/paper/2402.07642/) (2024)
- [Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey](https://mlsanity.com/paper/2511.05982/) (2025)
- [Global Clipper: Enhancing Safety and Reliability of Transformer-based Object Detection Models](https://mlsanity.com/paper/2406.03229/) (2024)
- [FORTALESA: Fault-Tolerant Reconfigurable Systolic Array for DNN Inference](https://mlsanity.com/paper/2503.04426/) (2025)
- [FLARE: One-Shot PE-Level Fault Localization in Systolic Arrays via Algebraic Test Vectors](https://mlsanity.com/paper/2605.08594/) (2026)
- [Explaining Unreliable Perception in Automated Driving: A Fuzzy-based Monitoring Approach](https://mlsanity.com/paper/2505.14407/) (2025)

## Abstract (arXiv)

We present a highly compact run-time monitoring approach for deep computer vision networks that extracts selected knowledge from only a few (down to merely two) hidden layers, yet can efficiently detect silent data corruption originating from both hardware memory and input faults. Building on the insight that critical faults typically manifest as peak or bulk shifts in the activation distribution of the affected network layers, we use strategically placed quantile markers to make accurate estimates about the anomaly of the current inference as a whole. Importantly, the detector component itself is kept algorithmically transparent to render the categorization of regular and abnormal behavior interpretable to a human. Our technique achieves up to ~96% precision and ~98% recall of detection. Compared to state-of-the-art anomaly detection techniques, this approach requires minimal compute overhead (as little as 0.3% with respect to non-supervised inference time) and contributes to the explainability of the model.