# Stealthy Attack on Algorithmic-Protected DNNs via Smart Bit Flipping

arXiv: https://arxiv.org/abs/2112.13162 · HTML: https://mlsanity.com/paper/2112.13162/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Dec 2021.

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

- [Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective](https://mlsanity.com/paper/2302.09457/) (2023)
- [ZOBNN: Zero-Overhead Dependable Design of Binary Neural Networks with Deliberately Quantized Parameters](https://mlsanity.com/paper/2407.04964/) (2024)
- [Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Lehman Go Indifferent](https://mlsanity.com/paper/2311.01205/) (2023)

## Abstract (arXiv)

Recently, deep neural networks (DNNs) have been deployed in safety-critical systems such as autonomous vehicles and medical devices. Shortly after that, the vulnerability of DNNs were revealed by stealthy adversarial examples where crafted inputs -- by adding tiny perturbations to original inputs -- can lead a DNN to generate misclassification outputs. To improve the robustness of DNNs, some algorithmic-based countermeasures against adversarial examples have been introduced thereafter. In this paper, we propose a new type of stealthy attack on protected DNNs to circumvent the algorithmic defenses: via smart bit flipping in DNN weights, we can reserve the classification accuracy for clean inputs but misclassify crafted inputs even with algorithmic countermeasures. To fool protected DNNs in a stealthy way, we introduce a novel method to efficiently find their most vulnerable weights and flip those bits in hardware. Experimental results show that we can successfully apply our stealthy attack against state-of-the-art algorithmic-protected DNNs.