# Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications

arXiv: https://arxiv.org/abs/2112.02819 · HTML: https://mlsanity.com/paper/2112.02819/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 88 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 30 of 43)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights](https://mlsanity.com/paper/1702.03044/) (2017)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach](https://mlsanity.com/paper/1807.04457/) (2018)
- [Dynamic Model Pruning with Feedback](https://mlsanity.com/paper/2006.07253/) (2020)
- [Guiding Deep Learning System Testing using Surprise Adequacy](https://mlsanity.com/paper/1808.08444/) (2018)
- [Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy](https://mlsanity.com/paper/1711.05852/) (2017)
- [Metamorphic Testing: A New Approach for Generating Next Test Cases](https://mlsanity.com/paper/2002.12543/) (2020)
- [TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing](https://mlsanity.com/paper/1807.10875/) (2018)

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

- [DiffGAN: A Test Generation Approach for Differential Testing of Deep Neural Networks for Image Analysis](https://mlsanity.com/paper/2410.19794/) (2024)

## Abstract (arXiv)

Model compression can significantly reduce the sizes of deep neural network (DNN) models, and thus facilitates the dissemination of sophisticated, sizable DNN models, especially for their deployment on mobile or embedded devices. However, the prediction results of compressed models may deviate from those of their original models. To help developers thoroughly understand the impact of model compression, it is essential to test these models to find those deviated behaviors before dissemination. However, this is a non-trivial task because the architectures and gradients of compressed models are usually not available. To this end, we propose DFLARE, a novel, search-based, black-box testing technique to automatically find triggering inputs that result in deviated behaviors in image classification tasks. DFLARE iteratively applies a series of mutation operations to a given seed image, until a triggering input is found. For better efficacy and efficiency, DFLARE models the search problem as Markov Chains and leverages the Metropolis-Hasting algorithm to guide the selection of mutation operators in each iteration. Further, DFLARE utilizes a novel fitness function to prioritize the mutated inputs that either cause large differences between two models' outputs, or trigger previously unobserved models' probability vectors. We evaluated DFLARE on 21 compressed models for image classification tasks with three datasets. The results show that DFLARE outperforms the baseline in terms of efficacy and efficiency. We also demonstrated that the triggering inputs found by DFLARE can be used to repair up to 48.48% deviated behaviors in image classification tasks and further decrease the effectiveness of DFLARE on the repaired models.