More Like this

1. Machine Learning Security as a Source of Unfairness in Human-Robot Interaction

   Richards, Luke E.; Matuszek, Cynthia (March 2023, Human-Robot Interaction (HRI) Workshop on Inclusive HRI II: Equity and Diversity in Design, Application, Methods, and Community (DEI HRI))

   Machine learning models that sense human speech, body placement, and other key features are commonplace in human-robot interaction. However, the deployment of such models in themselves is not without risk. Research in the security of machine learning examines how such models can be exploited and the risks associated with these exploits. Unfortunately, the threat models of risks produced by machine learning security do not incorporate the rich sociotechnical underpinnings of the defenses they propose; as a result, efforts to improve the security of machine learning models may actually increase the difference in performance across different demographic groups, yielding systems that have risk mitigation that work better for one group than another. In this work, we outline why current approaches to machine learning security present DEI concerns for the human-robot interaction community and where there are open areas for collaboration. 

   more » « less
2. An illustration of model agnostic explainability methods applied to environmental data

   https://doi.org/10.1002/env.2772  

   Wikle, Christopher K.; Datta, Abhirup; Hari, Bhava Vyasa; Boone, Edward L.; Sahoo, Indranil; Kavila, Indulekha; Castruccio, Stefano; Simmons, Susan J.; Burr, Wesley S.; Chang, Won (February 2023, Environmetrics)

   Historically, two primary criticisms statisticians have of machine learning and deep neural models is their lack of uncertainty quantification and the inability to do inference (i.e., to explain what inputs are important). Explainable AI has developed in the last few years as a sub‐discipline of computer science and machine learning to mitigate these concerns (as well as concerns of fairness and transparency in deep modeling). In this article, our focus is on explaining which inputs are important in models for predicting environmental data. In particular, we focus on three general methods for explainability that are model agnostic and thus applicable across a breadth of models without internal explainability: “feature shuffling”, “interpretable local surrogates”, and “occlusion analysis”. We describe particular implementations of each of these and illustrate their use with a variety of models, all applied to the problem of long‐lead forecasting monthly soil moisture in the North American corn belt given sea surface temperature anomalies in the Pacific Ocean. 

   more » « less
3. Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers

   Kenny Peng, Arunesh Mathur (November 2021, Advances in neural information processing systems)

   Machine learning datasets have elicited concerns about privacy, bias, and unethical applications, leading to the retraction of prominent datasets such as DukeMTMC, MS-Celeb-1M, and Tiny Images. In response, the machine learning community has called for higher ethical standards in dataset creation. To help inform these efforts, we studied three influential but ethically problematic face and person recognition datasets—Labeled Faces in the Wild (LFW), MS-Celeb-1M, and DukeMTMC— by analyzing nearly 1000 papers that cite them. We found that the creation of derivative datasets and models, broader technological and social change, the lack of clarity of licenses, and dataset management practices can introduce a wide range of ethical concerns. We conclude by suggesting a distributed approach to harm mitigation that considers the entire life cycle of a dataset. 

   more » « less
4. Mitigating dataset harms requires stewardship: Lessons from 1000 papers

   Peng, Kenny; Mathur, Arunesh; Narayanan, Arvind (December 2021, Advances in neural information processing systems)

   Machine learning datasets have elicited concerns about privacy, bias, and unethical applications, leading to the retraction of prominent datasets such as DukeMTMC, MS-Celeb-1M, and Tiny Images. In response, the machine learning community has called for higher ethical standards in dataset creation. To help inform these efforts, we studied three influential but ethically problematic face and person recognition datasets—Labeled Faces in the Wild (LFW), MS-Celeb-1M, and DukeMTMC— by analyzing nearly 1000 papers that cite them. We found that the creation of derivative datasets and models, broader technological and social change, the lack of clarity of licenses, and dataset management practices can introduce a wide range of ethical concerns. We conclude by suggesting a distributed approach to harm mitigation that considers the entire life cycle of a dataset. 

   more » « less
5. On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection

   https://doi.org/10.1145/3287560.3287590  

   Lai, Vivian; Tan, Chenhao (January 2019, FAT*)

   Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full automation. To realize the potential of machine learning for improving human decisions, it is important to understand how assistance from machine learning models affects human performance and human agency. In this paper, we use deception detection as a testbed and investigate how we can harness explanations and predictions of machine learning models to improve human performance while retaining human agency. We propose a spectrum between full human agency and full automation, and develop varying levels of machine assistance along the spectrum that gradually increase the influence of machine predictions. We find that without showing predicted labels, explanations alone slightly improve human performance in the end task. In comparison, human performance is greatly improved by showing predicted labels (>20% relative improvement) and can be further improved by explicitly suggesting strong machine performance. Interestingly, when predicted labels are shown, explanations of machine predictions induce a similar level of accuracy as an explicit statement of strong machine performance. Our results demonstrate a tradeoff between human performance and human agency and show that explanations of machine predictions can moderate this tradeoff. 

   more » « less