Astraea: Grammar-based Fairness Testing
- URL: http://arxiv.org/abs/2010.02542v5
- Date: Mon, 10 Jan 2022 08:11:15 GMT
- Title: Astraea: Grammar-based Fairness Testing
- Authors: Ezekiel Soremekun and Sakshi Udeshi and Sudipta Chattopadhyay
- Abstract summary: We propose a grammar-based fairness testing approach (called ASTRAEA)
ASTRAEA generates discriminatory inputs that reveal fairness violations in software systems.
It also provides fault diagnosis by isolating the cause of observed software bias.
- Score: 0.5672132510411463
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Software often produces biased outputs. In particular, machine learning (ML)
based software are known to produce erroneous predictions when processing
discriminatory inputs. Such unfair program behavior can be caused by societal
bias. In the last few years, Amazon, Microsoft and Google have provided
software services that produce unfair outputs, mostly due to societal bias
(e.g. gender or race). In such events, developers are saddled with the task of
conducting fairness testing. Fairness testing is challenging; developers are
tasked with generating discriminatory inputs that reveal and explain biases.
We propose a grammar-based fairness testing approach (called ASTRAEA) which
leverages context-free grammars to generate discriminatory inputs that reveal
fairness violations in software systems. Using probabilistic grammars, ASTRAEA
also provides fault diagnosis by isolating the cause of observed software bias.
ASTRAEA's diagnoses facilitate the improvement of ML fairness.
ASTRAEA was evaluated on 18 software systems that provide three major natural
language processing (NLP) services. In our evaluation, ASTRAEA generated
fairness violations with a rate of ~18%. ASTRAEA generated over 573K
discriminatory test cases and found over 102K fairness violations. Furthermore,
ASTRAEA improves software fairness by ~76%, via model-retraining.
Related papers
- Fairness Concerns in App Reviews: A Study on AI-based Mobile Apps [9.948068408730654]
Unfair AI-based systems, particularly unfair AI-based mobile apps, can pose difficulties for a significant proportion of the global population.
We first manually constructed a ground-truth dataset, including 1,132 fairness and 1,473 non-fairness reviews.
We developed and evaluated a set of machine learning and deep learning models that distinguish fairness reviews from non-fairness reviews.
arXiv Detail & Related papers (2024-01-16T03:43:33Z) - A First Look at Fairness of Machine Learning Based Code Reviewer
Recommendation [14.50773969815661]
This paper conducts the first study toward investigating the issue of fairness of ML applications in the software engineering (SE) domain.
Our empirical study demonstrates that current state-of-the-art ML-based code reviewer recommendation techniques exhibit unfairness and discriminating behaviors.
This paper also discusses the reasons why the studied ML-based code reviewer recommendation systems are unfair and provides solutions to mitigate the unfairness.
arXiv Detail & Related papers (2023-07-21T01:57:51Z) - BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models [73.29106813131818]
bias testing is currently cumbersome since the test sentences are generated from a limited set of manual templates or need expensive crowd-sourcing.
We propose using ChatGPT for the controllable generation of test sentences, given any arbitrary user-specified combination of social groups and attributes.
We present an open-source comprehensive bias testing framework (BiasTestGPT), hosted on HuggingFace, that can be plugged into any open-source PLM for bias testing.
arXiv Detail & Related papers (2023-02-14T22:07:57Z) - Invalidator: Automated Patch Correctness Assessment via Semantic and
Syntactic Reasoning [6.269370220586248]
In this paper, we propose a novel technique to automatically assess the correctness of APR-generated patches via semantic and syntactic reasoning.
We have conducted experiments on a dataset of 885 patches generated on real-world programs in Defects4J.
Experiment results show that INVALIDATOR correctly classified 79% overfitting patches, accounting for 23% more overfitting patches being detected by the best baseline.
arXiv Detail & Related papers (2023-01-03T14:16:32Z) - D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling
Algorithmic Bias [57.87117733071416]
We propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases.
A user can detect the presence of bias against a group by identifying unfair causal relationships in the causal network.
For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset.
arXiv Detail & Related papers (2022-08-10T03:41:48Z) - Understanding Unfairness in Fraud Detection through Model and Data Bias
Interactions [4.159343412286401]
We argue that algorithmic unfairness stems from interactions between models and biases in the data.
We study a set of hypotheses regarding the fairness-accuracy trade-offs that fairness-blind ML algorithms exhibit under different data bias settings.
arXiv Detail & Related papers (2022-07-13T15:18:30Z) - Fault-Aware Neural Code Rankers [64.41888054066861]
We propose fault-aware neural code rankers that can predict the correctness of a sampled program without executing it.
Our fault-aware rankers can significantly increase the pass@1 accuracy of various code generation models.
arXiv Detail & Related papers (2022-06-04T22:01:05Z) - A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms [19.86635585740634]
We present the conceptual idea and a first implementation of a bias-injection sandbox tool to investigate fairness consequences of various biases.
Unlike existing toolkits, ours provides a controlled environment to counterfactually inject biases in the ML pipeline.
In particular, we can test whether a given remedy can alleviate the injected bias by comparing the predictions resulting after the intervention with true labels in the unbiased regime-that is, before any bias injection.
arXiv Detail & Related papers (2022-04-21T16:12:19Z) - FairFil: Contrastive Neural Debiasing Method for Pretrained Text
Encoders [68.8687509471322]
We propose the first neural debiasing method for a pretrained sentence encoder, which transforms the pretrained encoder outputs into debiased representations via a fair filter network.
On real-world datasets, our FairFil effectively reduces the bias degree of pretrained text encoders, while continuously showing desirable performance on downstream tasks.
arXiv Detail & Related papers (2021-03-11T02:01:14Z) - BeFair: Addressing Fairness in the Banking Sector [54.08949958349055]
We present the initial results of an industrial open innovation project in the banking sector.
We propose a general roadmap for fairness in ML and the implementation of a toolkit called BeFair that helps to identify and mitigate bias.
arXiv Detail & Related papers (2021-02-03T16:37:10Z) - On the Robustness of Language Encoders against Grammatical Errors [66.05648604987479]
We collect real grammatical errors from non-native speakers and conduct adversarial attacks to simulate these errors on clean text data.
Results confirm that the performance of all tested models is affected but the degree of impact varies.
arXiv Detail & Related papers (2020-05-12T11:01:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.