DeepLocalize: Fault Localization for Deep Neural Networks

Wardat, Mohammad; Le, Wei; Rajan, Hridesh

doi:10.1109/icse43902.2021.00034

Cited by 63 publications

(75 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method helps to provide causality in software and reason about behavior of components based on the impact on outcome. This method can be extended further to evaluate the fairness of other software modules [52] in ML pipeline and localize faults [70]. Moreover, we found most of the stages exhibited bias, to a low [68].…”

Section: Discussionmentioning

confidence: 99%

Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline

Biswas

Rajan

2021

Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Softw

Self Cite

View full text Add to dashboard Cite

In recent years, many incidents have been reported where machine learning models exhibited discrimination among people based on race, sex, age, etc. Research has been conducted to measure and mitigate unfairness in machine learning models. For a machine learning task, it is a common practice to build a pipeline that includes an ordered set of data preprocessing stages followed by a classifier. However, most of the research on fairness has considered a single classifier based prediction task. What are the fairness impacts of the preprocessing stages in machine learning pipeline? Furthermore, studies showed that often the root cause of unfairness is ingrained in the data itself, rather than the model. But no research has been conducted to measure the unfairness caused by a specific transformation made in the data preprocessing stage. In this paper, we introduced the causal method of fairness to reason about the fairness impact of data preprocessing stages in ML pipeline. We leveraged existing metrics to define the fairness measures of the stages. Then we conducted a detailed fairness evaluation of the preprocessing stages in 37 pipelines collected from three different sources. Our results show that certain data transformers are causing the model to exhibit unfairness. We identified a number of fairness patterns in several categories of data transformers. Finally, we showed how the local fairness of a preprocessing stage composes in the global fairness of the pipeline. We used the fairness composition to choose appropriate downstream transformer that mitigates unfairness in the machine learning pipeline. CCS CONCEPTS• Software and its engineering → Software creation and management; • Computing methodologies → Machine learning.

show abstract

Section: Discussionmentioning

confidence: 99%

Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline

Biswas

Rajan

2021

Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Softw

Self Cite

View full text Add to dashboard Cite

show abstract

“…Similarly, Zhang et al [60] implement DeepRoad, which applies Generative Adversarial Networks (GANs) [24] to test DL-based self-driving cars. Besides, there are also many researches focus on detecting different kinds of bugs in model structures or training parameter settings [51,62]. For instance, Zhang et al [62] propose DEBAR, a static analysis approach for detecting numerical bugs in DL models.…”

Section: Related Workmentioning

confidence: 99%

Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzing

Gu¹,

Luo²,

Zhou³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning (DL) techniques are proven effective in many challenging tasks, and become widely-adopted in practice. However, previous work has shown that DL libraries, the basis of building and executing DL models, contain bugs and can cause severe consequences. Unfortunately, existing testing approaches still cannot comprehensively exercise DL libraries. They utilize existing trained models and only detect bugs in model inference phase. In this work we propose Muffin to address these issues. To this end, Muffin applies a specifically-designed model fuzzing approach, which allows it to generate diverse DL models to explore the target library, instead of relying only on existing trained models. Muffin makes differential testing feasible in the model training phase by tailoring a set of metrics to measure the inconsistencies between different DL libraries. In this way, Muffin can best exercise the library code to detect more bugs. To evaluate the effectiveness of Muffin, we conduct experiments on three widely-used DL libraries. The results demonstrate that Muffin can detect 39 new bugs in the latest release versions of popular DL libraries, including Tensorflow, CNTK, and Theano. CCS Concepts: • Software and its engineering → Software testing and debugging; Software libraries and repositories.

show abstract

“…In contrast to this, AequeVox's fault localisation algorithm identifies utterances spoken by a group which are likely to be not recognised by ASR systems in the presence of a destructive interference (such as noise). Recent fault localization approaches either aim to highlight the neurons [16] or training code [56] that are responsible for a fault during inference. In contrast, AequeVox highlights words that are likely to be transcribed wrongly without having any access to the ground truth transcription and with only blackbox access to the ASR system.…”

Section: Related Workmentioning

confidence: 99%

AequeVox: Automated Fairness Testing of Speech Recognition Systems

Sathiesh¹,

Udeshi²,

Chattopadhyay³

2021

Preprint

View full text Add to dashboard Cite

Automatic Speech Recognition (ASR) systems have become ubiquitous. They can be found in a variety of form factors and are increasingly important in our daily lives. As such, ensuring that these systems are equitable to different subgroups of the population is crucial. In this paper, we introduce, AequeVox, an automated testing framework for evaluating the fairness of ASR systems. AequeVox simulates different environments to assess the effectiveness of ASR systems for different populations. In addition, we investigate whether the chosen simulations are comprehensible to humans. We further propose a fault localization technique capable of identifying words that are not robust to these varying environments. Both components of AequeVox are able to operate in the absence of ground truth data. We evaluated AequeVox on speech from four different datasets using three different commercial ASRs. Our experiments reveal that non-native English, female and Nigerian English speakers generate 109%, 528.5% and 156.9% more errors, on average than native English, male and UK Midlands speakers, respectively. Our user study also reveals that 82.9% of the simulations (employed through speech transformations) had a comprehensibility rating above seven (out of ten), with the lowest rating being 6.78. This further validates the fairness violations discovered by AequeVox. Finally, we show that the non-robust words, as predicted by the fault localization technique embodied in AequeVox, show 223.8% more errors than the predicted robust words across all ASRs.

show abstract

DeepLocalize: Fault Localization for Deep Neural Networks

Cited by 63 publications

References 28 publications

Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline

Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline

Muffin: Testing Deep Learning Libraries via Neural Architecture Fuzzing

AequeVox: Automated Fairness Testing of Speech Recognition Systems

Contact Info

Product

Resources

About