Deep neural networks (DNNs) have demonstrated superior performance over classical machine learning to support many features in safety-critical systems. Although DNNs are now widely used in such systems (e.g., self driving cars), there is limited progress regarding automated support for functional safety analysis in DNN-based systems. For example, the identification of root causes of errors, to enable both risk analysis and DNN retraining, remains an open problem. In this paper, we propose SAFE, a black-box approach to automatically characterize the root causes of DNN errors. SAFE relies on a transfer learning model pre-trained on ImageNet to extract the features from error-inducing images. It then applies a density-based clustering algorithm to detect arbitrary shaped clusters of images modeling plausible causes of error. Last, clusters are used to effectively retrain and improve the DNN. The black-box nature of SAFE is motivated by our objective not to require changes or even access to the DNN internals to facilitate adoption. Experimental results show the superior ability of SAFE in identifying different root causes of DNN errors based on case studies in the automotive domain. It also yields significant improvements in DNN accuracy after retraining, while saving significant execution time and memory when compared to alternatives.
Supporting Safety Analysis of Image-processing DNNs through Clustering-based Approaches
SnT Centre, University of Luxembourg（卢森堡大学SnT中心）；University of Luxembourg（卢森堡大学）；University of Ottawa（渥太华大学）；Lero Centre, University of Limerick（利默里克大学Lero中心）；School of EECS, University of Ottawa（渥太华大学电子工程与计算机科学学院）
SnT Centre for Security, Reliability and Trust, University of Luxembourg（卢森堡大学安全、可靠性与信任中心）；University of Ottawa（渥太华大学）
Deep neural networks (DNNs) are increasingly important in safety-critical systems, for example in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the functional safety of DNN-based components. We observe three major challenges with existing practices regarding DNNs in safety-critical systems: (1) scenarios that are underrepresented in the test set may lead to serious safety violation risks, but may, however, remain unnoticed; (2) characterizing such high-risk scenarios is critical for safety analysis; (3) retraining DNNs to address these risks is p…
Abstract knowledge is deeply grounded in many computer-based applications. An important research area of Artificial Intelligence (AI) deals with the automatic derivation of knowledge from data. Machine learning offers the according algorithms. One area of research focuses on the development of biologically inspired learning algorithms. The respective machine learning methods are based on neurological concepts so that they can systematically derive knowledge from data and store it. One type of machine learning algorithms that can be categorized as "deep learning" model is referred to as Deep Ne…
University of Luxembourg（卢森堡大学）；University of Ottawa（渥太华大学）
We present HUDD, a tool that supports safety analysis practices for systems enabled by Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN. HUDD stands for Heatmap-based Unsupervised Debugging of DNNs, it automatically clusters error-inducing images whose results are due to common subsets of DNN neurons. The intent is for the generated clusters to group error-inducing images having common characteristics, that is, having a common root cause. HUDD identifies root causes by applying a clustering algorithm to matrices (i.e., heatmaps) cap…
University of Luxembourg（卢森堡大学）；University of Ottawa（渥太华大学）；IEE S.A.（IEE股份有限公司）
When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i.e., erroneous outputs) observed during testing. For DNNs processing images, engineers visually inspect all failure-inducing images to determine common characteristics among them. Such characteristics correspond to hazard-triggering events (e.g., low illumination) that are essential inputs for safety analysis. Though informative, such activity is expensive and error-prone. To support such safety analysis practices, we propose SEDE, a technique that genera…
Repairing Deep Neural Networks Based on Behavior Imitation
National University of Defense Technology（国防科技大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Fujitsu Limited（富士通有限公司）；National Institute of Informatics（国立信息学研究所）
Systematic techniques to improve quality of deep neural networks (DNNs) are critical given the increasing demand for practical applications including safety-critical ones. The key challenge comes from the little controllability in updating DNNs. Retraining to fix some behavior often has a destructive impact on other behavior, causing regressions, i.e., the updated DNN fails with inputs correctly handled by the original one. This problem is crucial when engineers are required to investigate failures in intensive assurance activities for safety or trust. Search-based repair techniques for DNNs h…
Deep Neural Networks (DNNs) have been widely used in software making decisions impacting people's lives. However, they have been found to exhibit severe erroneous behaviors that may lead to unfortunate outcomes. Previous work shows that such misbehaviors often occur due to class property violations rather than errors on a single image. Although methods for detecting such errors have been proposed, fixing them has not been studied so far. Here, we propose a generic method called Weighted Regularization (WR) consisting of five concrete methods targeting the error-producing classes to fix the DNN…
Over the past few years, deep neural networks (DNNs) have been continuously expanding their real-world applications for source code processing tasks across the software engineering domain, e.g., clone detection, code search, comment generation. Although quite a few recent works have been performed on testing of DNNs in the context of image and speech processing, limited progress has been achieved so far on DNN testing in the context of source code processing, that exhibits rather unique characteristics and challenges. In this paper, we propose a search-based testing framework for DNNs of sourc…
The application of Deep Neural Networks (DNNs) to a broad variety of tasks demands methods for coping with the complex and opaque nature of these architectures. When a gold standard is available, performance assessment treats the DNN as a black box and computes standard metrics based on the comparison of the predictions with the ground truth. A deeper understanding of performances requires going beyond such evaluation metrics to diagnose the model behavior and the prediction errors. This goal can be pursued in two complementary ways. On one side, model interpretation techniques "open the box" …
Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection
School of Mathematical Sciences, Peking University, China（北京大学数学科学学院）；School of Computer Science, University of Bristol, UK（英国布里斯托大学计算机科学学院）；School of Control Science and Engineering, Zhejiang University, China（浙江大学控制科学与工程学院）
提出 NFARD，利用神经元功能与正常样本检测 DNN 复用关系，支持白盒、黑盒及异构场景，并构建 Reuse Zoo，检测 F1 最高达 1.0。
Deep Neural Networks (DNNs) are being deployed in a wide range of settings today, from safety-critical applications like autonomous driving to commercial applications involving image classifications. However, recent research has shown that DNNs can be brittle to even slight variations of the input data. Therefore, rigorous testing of DNNs has gained widespread attention. While DNN robustness under norm-bound perturbation got significant attention over the past few years, our knowledge is still limited when natural variants of the input images come. These natural variants, e.g. a rotated or a r…
