# New Security Challenges on Machine Learning Inference Engine: Chip Cloning and Model Reverse Engineering

arXiv: https://arxiv.org/abs/2003.09739 · HTML: https://mlsanity.com/paper/2003.09739/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [SoK: A Systems Perspective on Compound AI Threats and Countermeasures](https://mlsanity.com/paper/2411.13459/) (2024)
- [Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems](https://mlsanity.com/paper/2603.12023/) (2026)
- [Edge Deep Learning Model Protection via Neuron Authorization](https://mlsanity.com/paper/2303.12397/) (2023)

## Abstract (arXiv)

Machine learning inference engine is of great interest to smart edge computing. Compute-in-memory (CIM) architecture has shown significant improvements in throughput and energy efficiency for hardware acceleration. Emerging non-volatile memory technologies offer great potential for instant on and off by dynamic power gating. Inference engine is typically pre-trained by the cloud and then being deployed to the filed. There are new attack models on chip cloning and neural network model reverse engineering. In this paper, we propose countermeasures to the weight cloning and input-output pair attacks. The first strategy is the weight fine-tune to compensate the analog-to-digital converter (ADC) offset for a specific chip instance while inducing significant accuracy drop for cloned chip instances. The second strategy is the weight shuffle and fake rows insertion to allow accurate propagation of the activations of the neural network only with a key.