Secure Deep Learning Engineering: A Software Quality Assurance Perspective

Ма, Лей; Juefei-Xu, Felix; Xue, Minhui; Hu, Qiang; Chen, Sen; Li, Bo; Liu, Yang; Zhao, Jianjun; Yin, Jianxiong; See, Simon

doi:10.48550/arxiv.1810.04538

Cited by 7 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We confirmed the usefulness of the proposed criteria on ASRs and showed that the fuzzing framework is effective in exposing real-world defects. In the future, we plan to evaluate our techniques on more diverse application domains, towards providing quality assurance solution for DL systems life-cycle [57].…”

Section: Discussionmentioning

confidence: 99%

DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems

Du,

Xie,

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning (DL) defines a data-driven programming paradigm that automatically composes the system decision logic from the training data. In company with the data explosion and hardware acceleration during the past decade, DL achieves tremendous success in many cutting-edge applications. However, even the state-of-the-art DL systems still suffer from quality and reliability issues. It was only until recently that some preliminary progress was made in testing feed-forward DL systems.In contrast to feed-forward DL systems, recurrent neural networks (RNN) follow a very different architectural design, implementing temporal behaviours and "memory" with loops and internal states. Such stateful nature of RNN contributes to its success in handling sequential inputs such as audio, natural languages and video processing, but also poses new challenges for quality assurance. In this paper, we initiate the very first step towards testing RNN-based stateful DL systems. We model RNN as an abstract state transition system, based on which we define a set of test coverage criteria specialized for stateful DL systems. Moreover, we propose an automated testing framework, DeepCruiser, which systematically generates tests in large scale to uncover defects of stateful DL systems with coverage guidance. Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.

show abstract

Section: Discussionmentioning

confidence: 99%

DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems

Du,

Xie,

et al. 2018

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although over the past few years deep learning has been the key driving force in self-driving industry, it also raises safety and security issues due to the lack of interpretability and transparency [27]. Stop line detection is a safety-critical application, and hence understanding how the network retrieves information from different channels and makes decisions is very crucial.…”

Section: F Visual Interpretationmentioning

confidence: 99%

Holistic Grid Fusion Based Stop Line Estimation

Tafazzoli

Zhang

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

Intersection scenarios provide the most complex traffic situations in Autonomous Driving and Driving Assistance Systems. Knowing where to stop in advance in an intersection is an essential parameter in controlling the longitudinal velocity of the vehicle. Most of the existing methods in literature solely use cameras to detect stop lines, which is typically not sufficient in terms of detection range. To address this issue, we propose a method that takes advantage of fused multi-sensory data including stereo camera and lidar as input and utilizes a carefully designed convolutional neural network architecture to detect stop lines. Our experiments show that the proposed approach can improve detection range compared to camera data alone, works under heavy occlusion without observing the ground markings explicitly, is able to predict stop lines for all lanes and allows detection at a distance up to 50 meters.

show abstract

“…DeepStellar [11] employs the coverage criteria and fuzzing technique for testing the recurrent neural network. More discussions on the progress of deep learning testing can be referred to the recent survey [67,38]. Different from these testing techniques, our work mainly focuses on repairing DNNs and enhance their robustness and generalization ability, which can be considered as the downstream tasks of DNN testing.…”

Section: Dnn Testingmentioning

confidence: 99%

ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks

Hua¹,

Wang²,

Guo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Over the past few years, deep neural networks (DNNs) have achieved tremendous success and have been continuously applied in many application domains. However, during the practical deployment in the industrial tasks, DNNs are found to be erroneous-prone due to various reasons such as overfitting, lacking robustness to real-world corruptions during practical usage. To address these challenges, many recent attempts have been made to repair DNNs for version updates under practical operational contexts by updating weights (i.e., network parameters) through retraining, fine-tuning, or direct weight fixing at a neural level. Nevertheless, existing solutions often neglect the effects of neural network architecture and weight relationships across neurons and layers. In this work, as the first attempt, we initiate to repair DNNs by jointly optimizing the architecture and weights at a higher (i.e., block) level. We first perform empirical studies to investigate the limitation of whole network-level and layer-level repairing, which motivates us to explore a novel repairing direction for DNN repair at the block level. To this end, we need to further consider techniques to address two key technical challenges, i.e., block localization, where we should localize the targeted block that we need to fix; and how to perform joint architecture and weight repairing. Specifically, we first propose adversarial-aware spectrum analysis for vulnerable block localization that considers the neurons' status and weights' gradients in blocks during the forward and backward processes, which enables more accurate candidate block localization for repairing even under a few examples. Then, we further propose the architecture-oriented search-based repairing that relaxes the targeted block to a continuous repairing search space at higher deep feature levels. By jointly optimizing the architecture and weights in that space, we can identify a much better block architecture. We implement our proposed repairing techniques as a tool, named ArchRepair , and conduct extensive experiments to validate the proposed method. The results show that our method can not only repair but also enhance accuracy & robustness, outperforming the state-of-the-art DNN repair techniques.

show abstract

Secure Deep Learning Engineering: A Software Quality Assurance Perspective

Cited by 7 publications

References 29 publications

DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems

DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems

Holistic Grid Fusion Based Stop Line Estimation

ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks

Contact Info

Product

Resources

About