# Forensicability of Deep Neural Network Inference Pipelines

arXiv: https://arxiv.org/abs/2102.00921 · HTML: https://mlsanity.com/paper/2102.00921/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 1 Feb 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [DeepFakes: a New Threat to Face Recognition? Assessment and Detection](https://mlsanity.com/paper/1812.08685/) (2018)
- [Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware](https://mlsanity.com/paper/1806.03287/) (2018)
- [Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics](https://mlsanity.com/paper/1612.07767/) (2016)
- [SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud](https://mlsanity.com/paper/1706.10268/) (2017)

## Built on by (most cited first, 5 of 5)

- [VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Traces](https://mlsanity.com/paper/2211.15775/) (2022)
- [Hardware and Software Platform Inference](https://mlsanity.com/paper/2411.05197/) (2024)
- [iNNformant: Boundary Samples as Telltale Watermarks](https://mlsanity.com/paper/2106.07303/) (2021)
- [Quantamination: Dynamic Quantization Leaks Your Data Across the Batch](https://mlsanity.com/paper/2604.26505/) (2026)
- [FloatDoor: Platform-Triggered Backdoors in LLMs](https://mlsanity.com/paper/2606.19535/) (2026)

## Abstract (arXiv)

We propose methods to infer properties of the execution environment of machine learning pipelines by tracing characteristic numerical deviations in observable outputs. Results from a series of proof-of-concept experiments obtained on local and cloud-hosted machines give rise to possible forensic applications, such as the identification of the hardware platform used to produce deep neural network predictions. Finally, we introduce boundary samples that amplify the numerical deviations in order to distinguish machines by their predicted label only.