# Backdooring Convolutional Neural Networks via Targeted Weight Perturbations

## TL;DR

This paper introduces a novel backdoor attack method on CNNs, especially facial recognition systems, by applying targeted weight perturbations, revealing significant security vulnerabilities in these models.

## Contribution

The paper presents a new backdoor attack technique using targeted weight perturbations, demonstrating its effectiveness on CNNs like ResNet-50 for facial recognition.

## Key findings

- Increased false acceptance rates for targeted inputs
- Preservation of legitimate class accuracy
- Effective attack demonstrated on ResNet-50

## Abstract

We present a new type of backdoor attack that exploits a vulnerability of convolutional neural networks (CNNs) that has been previously unstudied. In particular, we examine the application of facial recognition. Deep learning techniques are at the top of the game for facial recognition, which means they have now been implemented in many production-level systems. Alarmingly, unlike other commercial technologies such as operating systems and network devices, deep learning-based facial recognition algorithms are not presently designed with security requirements or audited for security vulnerabilities before deployment. Given how young the technology is and how abstract many of the internal workings of these algorithms are, neural network-based facial recognition systems are prime targets for security breaches. As more and more of our personal information begins to be guarded by facial recognition (e.g., the iPhone X), exploring the security vulnerabilities of these systems from a penetration testing standpoint is crucial. Along these lines, we describe a general methodology for backdooring CNNs via targeted weight perturbations. Using a five-layer CNN and ResNet-50 as case studies, we show that an attacker is able to significantly increase the chance that inputs they supply will be falsely accepted by a CNN while simultaneously preserving the error rates for legitimate enrolled classes.