# Needle in a Haystack: Detecting Subtle Malicious Edits to Additive Manufacturing G-code Files

arXiv: https://arxiv.org/abs/2111.12746 · HTML: https://mlsanity.com/paper/2111.12746/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security.
- Builds on 2 of its 20 references that are in the map.
- First posted on arXiv 24 Nov 2021.

## Placed in

- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 2 of 2)

- [dr0wned - Cyber-Physical Attack with Additive Manufacturing](https://mlsanity.com/paper/1609.00133/) (2016)
- [FLAW3D: A Trojan-based Cyber Attack on the Physical Outcomes of Additive Manufacturing](https://mlsanity.com/paper/2104.09562/) (2021)

## Built on by (most cited first, 4 of 4)

- [LLM-3D Print: Large Language Models To Monitor and Control 3D Printing](https://mlsanity.com/paper/2408.14307/) (2024)
- [FDM-Bench: A Comprehensive Benchmark for Evaluating Large Language Models in Additive Manufacturing Tasks](https://mlsanity.com/paper/2412.09819/) (2024)
- [Engineering Attack Vectors and Detecting Anomalies in Additive Manufacturing](https://mlsanity.com/paper/2601.00384/) (2026)
- [LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing](https://mlsanity.com/paper/2605.03328/) (2026)

## Abstract (arXiv)

Increasing usage of Digital Manufacturing (DM) in safety-critical domains is increasing attention on the cybersecurity of the manufacturing process, as malicious third parties might aim to introduce defects in digital designs. In general, the DM process involves creating a digital object (as CAD files) before using a slicer program to convert the models into printing instructions (e.g. g-code) suitable for the target printer. As the g-code is an intermediate machine format, malicious edits may be difficult to detect, especially when the golden (original) models are not available to the manufacturer. In this work we aim to quantify this hypothesis through a red-team/blue-team case study, whereby the red-team aims to introduce subtle defects that would impact the properties (strengths) of the 3D printed parts, and the blue-team aims to detect these modifications in the absence of the golden models. The case study had two sets of models, the first with 180 designs (with 2 compromised using 2 methods) and the second with 4320 designs (with 60 compromised using 6 methods). Using statistical modelling and machine learning (ML), the blue-team was able to detect all the compromises in the first set of data, and 50 of the compromises in the second.