# Guiding the retraining of convolutional neural networks against adversarial inputs

arXiv: https://arxiv.org/abs/2207.03689 · HTML: https://mlsanity.com/paper/2207.03689/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 77 references that are in the map.
- First posted on arXiv 8 Jul 2022.

## Builds on (most cited first, 30 of 36)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Detecting Adversarial Samples from Artifacts](https://mlsanity.com/paper/1703.00410/) (2017)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [A Survey of the Recent Architectures of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1901.06032/) (2019)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Technical Report on the CleverHans v2.1.0 Adversarial Examples Library](https://mlsanity.com/paper/1610.00768/) (2016)
- [Guiding Deep Learning System Testing using Surprise Adequacy](https://mlsanity.com/paper/1808.08444/) (2018)
- [Software Engineering for AI-Based Systems: A Survey](https://mlsanity.com/paper/2105.01984/) (2021)
- [Adversarial Machine Learning in Image Classification: A Survey Towards the Defender's Perspective](https://mlsanity.com/paper/2009.03728/) (2020)
- [Requirements Engineering for Machine Learning: Perspectives from Data Scientists](https://mlsanity.com/paper/1908.04674/) (2019)
- [A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning](https://mlsanity.com/paper/2012.13628/) (2020)
- [Test Selection for Deep Learning Systems](https://mlsanity.com/paper/1904.13195/) (2019)
- [Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)](https://mlsanity.com/paper/2205.00664/) (2022)
- [Importance-Driven Deep Learning System Testing](https://mlsanity.com/paper/2002.03433/) (2020)
- [Adversarial Examples on Object Recognition: A Comprehensive Survey](https://mlsanity.com/paper/2008.04094/) (2020)
- [Reducing DNN Labelling Cost using Surprise Adequacy: An Industrial Case Study for Autonomous Driving](https://mlsanity.com/paper/2006.00894/) (2020)
- [A Review and Refinement of Surprise Adequacy](https://mlsanity.com/paper/2103.05939/) (2021)
- [Integration of Convolutional Neural Networks in Mobile Applications](https://mlsanity.com/paper/2103.07286/) (2021)

## Built on by (most cited first, 1 of 1)

- [Towards green AI-based software systems: an architecture-centric approach (GAISSA)](https://mlsanity.com/paper/2307.09964/) (2023)

## Abstract (arXiv)

Background: When using deep learning models, there are many possible vulnerabilities and some of the most worrying are the adversarial inputs, which can cause wrong decisions with minor perturbations. Therefore, it becomes necessary to retrain these models against adversarial inputs, as part of the software testing process addressing the vulnerability to these inputs. Furthermore, for an energy efficient testing and retraining, data scientists need support on which are the best guidance metrics and optimal dataset configurations. Aims: We examined four guidance metrics for retraining convolutional neural networks and three retraining configurations. Our goal is to improve the models against adversarial inputs regarding accuracy, resource utilization and time from the point of view of a data scientist in the context of image classification. Method: We conducted an empirical study in two datasets for image classification. We explore: (a) the accuracy, resource utilization and time of retraining convolutional neural networks by ordering new training set by four different guidance metrics (neuron coverage, likelihood-based surprise adequacy, distance-based surprise adequacy and random), (b) the accuracy and resource utilization of retraining convolutional neural networks with three different configurations (from scratch and augmented dataset, using weights and augmented dataset, and using weights and only adversarial inputs). Results: We reveal that retraining with adversarial inputs from original weights and by ordering with surprise adequacy metrics gives the best model w.r.t. the used metrics. Conclusions: Although more studies are necessary, we recommend data scientists to use the above configuration and metrics to deal with the vulnerability to adversarial inputs of deep learning models, as they can improve their models against adversarial inputs without using many inputs.