scispace - formally typeset
Search or ask a question
Author

Sameep Mehta

Bio: Sameep Mehta is an academic researcher from IBM. The author has contributed to research in topics: Service (business) & Resource (project management). The author has an hindex of 22, co-authored 160 publications receiving 2093 citations. Previous affiliations of Sameep Mehta include Lady Hardinge Medical College & All India Institute of Medical Sciences.


Papers
More filters
Posted Content
TL;DR: A new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms.
Abstract: Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license {this https URL). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (this https URL) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking. A built-in testing infrastructure maintains code quality.

501 citations

Journal ArticleDOI
TL;DR: This paper envisiones an SDoC for AI services to contain purpose, performance, safety, security, and provenance information to be completed and voluntarily released by AI service providers for examination by consumers.
Abstract: Accuracy is an important concern for suppliers of artificial intelligence (AI) services, but considerations beyond accuracy, such as safety (which includes fairness and explainability), security, and provenance, are also critical elements to engender consumers’ trust in a service. Many industries use transparent, standardized, but often not legally required documents called supplier's declarations of conformity (SDoCs) to describe the lineage of a product along with the safety and performance testing it has undergone. SDoCs may be considered multidimensional fact sheets that capture and quantify various aspects of the product and its development to make it worthy of consumers’ trust. In this article, inspired by this practice, we propose FactSheets to help increase trust in AI services. We envision such documents to contain purpose, performance, safety, security, and provenance information to be completed by AI service providers for examination by consumers. We suggest a comprehensive set of declaration items tailored to AI in the Appendix of this article.

243 citations

Posted Content
TL;DR: This paper proposes a new method of crafting adversarial text samples by modification of the original samples, which works best for the datasets which have sub-categories within each of the classes of examples.
Abstract: Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being mis-classified by the classifier. However, the samples are perceived to be drawn from entirely different classes and thus it becomes hard to detect the adversarial samples. Most of the prior works have been focused on synthesizing adversarial samples in the image domain. In this paper, we propose a new method of crafting adversarial text samples by modification of the original samples. Modifications of the original text samples are done by deleting or replacing the important or salient words in the text or by introducing new words in the text sample. Our algorithm works best for the datasets which have sub-categories within each of the classes of examples. While crafting adversarial samples, one of the key constraint is to generate meaningful sentences which can at pass off as legitimate from language (English) viewpoint. Experimental results on IMDB movie review dataset for sentiment analysis and Twitter dataset for gender detection show the efficiency of our proposed method.

189 citations

Proceedings ArticleDOI
26 Oct 2010
TL;DR: These findings show that coupling the detection and anti-rumor strategy by embedding agents in the network, the authors call them beacons, is an effective means of fighting the spread of rumor, even if these beacons do not share information.
Abstract: In this paper we study and evaluate rumor-like methods for combating the spread of rumors on a social network. We model rumor spread as a diffusion process on a network and suggest the use of an "anti-rumor" process similar to the rumor process. We study two natural models by which these anti-rumors may arise. The main metrics we study are the belief time, i.e., the duration for which a person believes the rumor to be true and point of decline, i.e., point after which anti-rumor process dominates the rumor process. We evaluate our methods by simulating rumor spread and anti-rumor spread on a data set derived from the social networking site Twitter and on a synthetic network generated according to the Watts and Strogatz model. We find that the lifetime of a rumor increases if the delay in detecting it increases, and the relationship is at least linear. Further our findings show that coupling the detection and anti-rumor strategy by embedding agents in the network, we call them beacons, is an effective means of fighting the spread of rumor, even if these beacons do not share information.

125 citations

Proceedings ArticleDOI
03 Dec 2018
TL;DR: A model extraction monitor that quantifies the extraction status of models by continually observing the API query and response streams of users is introduced and two novel strategies that measure either the information gain or the coverage of the feature space spanned by user queries to estimate the learning rate of individual and colluding adversaries are presented.
Abstract: Machine learning models deployed on the cloud are susceptible to several security threats including extraction attacks. Adversaries may abuse a model's prediction API to steal the model thus compromising model confidentiality, privacy of training data, and revenue from future query payments. This work introduces a model extraction monitor that quantifies the extraction status of models by continually observing the API query and response streams of users. We present two novel strategies that measure either the information gain or the coverage of the feature space spanned by user queries to estimate the learning rate of individual and colluding adversaries. Both approaches have low computational overhead and can easily be offered as services to model owners to warn them against state of the art extraction attacks. We demonstrate empirical performance results of these approaches for decision tree and neural network models using open source datasets and BigML MLaaS platform.

98 citations


Cited by
More filters
Journal ArticleDOI
09 Mar 2018-Science
TL;DR: A large-scale analysis of tweets reveals that false rumors spread further and faster than the truth, and false news was more novel than true news, which suggests that people were more likely to share novel information.
Abstract: We investigated the differential diffusion of all of the verified true and false news stories distributed on Twitter from 2006 to 2017. The data comprise ~126,000 stories tweeted by ~3 million people more than 4.5 million times. We classified news as true or false using information from six independent fact-checking organizations that exhibited 95 to 98% agreement on the classifications. Falsehood diffused significantly farther, faster, deeper, and more broadly than the truth in all categories of information, and the effects were more pronounced for false political news than for false news about terrorism, natural disasters, science, urban legends, or financial information. We found that false news was more novel than true news, which suggests that people were more likely to share novel information. Whereas false stories inspired fear, disgust, and surprise in replies, true stories inspired anticipation, sadness, joy, and trust. Contrary to conventional wisdom, robots accelerated the spread of true and false news at the same rate, implying that false news spreads more than the truth because humans, not robots, are more likely to spread it.

4,241 citations

01 Jan 2012

3,692 citations

21 Jan 2018
TL;DR: It is shown that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men, in commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition.
Abstract: The paper “Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification” by Joy Buolamwini and Timnit Gebru, that will be presented at the Conference on Fairness, Accountability, and Transparency (FAT*) in February 2018, evaluates three commercial API-based classifiers of gender from facial images, including IBM Watson Visual Recognition. The study finds these services to have recognition capabilities that are not balanced over genders and skin tones [1]. In particular, the authors show that the highest error involves images of dark-skinned women, while the most accurate result is for light-skinned men.

2,528 citations

Posted Content
TL;DR: This survey investigated different real-world applications that have shown biases in various ways, and created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems.
Abstract: With the widespread use of AI systems and applications in our everyday lives, it is important to take fairness issues into consideration while designing and engineering these types of systems. Such systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that the decisions do not reflect discriminatory behavior toward certain groups or populations. We have recently seen work in machine learning, natural language processing, and deep learning that addresses such challenges in different subdomains. With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them. In this survey we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined in order to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and how they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

1,571 citations