Match!
Supriyo Chakraborty
IBM
Machine learningInformation privacyData miningInferenceComputer science
75Publications
14H-index
698Citations
What is this?
Publications 64
Newest
#1Richard Tomsett (IBM)H-Index: 6
#2Dan Harborne (Cardiff University)H-Index: 1
Last. Alun Preece (Cardiff University)H-Index: 32
view all 5 authors...
Saliency maps are a popular approach to creating post-hoc explanations of image classifier outputs. These methods produce estimates of the relevance of each pixel to the classification output score, which can be displayed as a saliency map that highlights important pixels. Despite a proliferation of such methods, little effort has been made to quantify how good these saliency maps are at capturing the true relevance of the pixels to the classifier output (i.e. their "fidelity"). We therefore inv...
1 Citations
#1Moustafa Alzantot (UCLA: University of California, Los Angeles)H-Index: 10
#2Yash Sharma (Cooper Union)H-Index: 9
Last. Mani Srivastava (UCLA: University of California, Los Angeles)H-Index: 91
view all 6 authors...
6 CitationsSource
#1Dinesh C. VermaH-Index: 21
#2Graham WhiteH-Index: 1
Last. Greg CirincioneH-Index: 4
view all 6 authors...
2 CitationsSource
#1Richard TomsettH-Index: 6
Last. Supriyo ChakrabortyH-Index: 14
view all 3 authors...
Source
Jan 1, 2019 in AAAI (National Conference on Artificial Intelligence)
#1Amanda Coston (CMU: Carnegie Mellon University)H-Index: 1
Last. Supriyo Chakraborty (IBM)H-Index: 14
view all 7 authors...
8 CitationsSource
#2Supriyo Chakraborty (IBM)H-Index: 14
Last. Dinesh C. Verma (IBM)H-Index: 21
view all 3 authors...
Distributed learning has emerged as a useful tool for analyzing data stored in multiple geographic locations, especially when the distributed data sets are large and hard to move around, or the data owner is reluctant to put data into the Cloud due to privacy concerns. In distributed learning, only the locally computed models are uploaded to the fusion server, which however may still cause privacy issues since the fusion server could implement various inference attacks from its observations. To ...
Source
#1Yeon-sup Lim (IBM)H-Index: 12
#2Mudhakar Srivatsa (IBM)H-Index: 24
Last. Ian Taylor (Cardiff University)H-Index: 32
view all 4 authors...
Privacy becomes one of the important issues in data-driven applications. The advent of non-PC devices such as Internet-of-Things (IoT) devices for data-driven applications leads to needs for light-weight data anonymization. In this paper, we develop an anonymization framework that expedites model learning in parallel and generates deployable models for devices with low computing capability. We evaluate our framework with various settings such as different data schema and characteristics. Our res...
Source
#2Supriyo ChakrabortyH-Index: 14
Last. Seraphin CaloH-Index: 22
view all 4 authors...
Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this work, we explore the threat of model poisoning attacks on federated learning initiated by a single, non-colluding malicious agent where the adversarial objective is to cause the model to misclassify a set of chosen inputs with high confidence. We explore a number...
13 Citations
#1Alun PreeceH-Index: 32
#2Dan HarborneH-Index: 1
Last. Supriyo ChakrabortyH-Index: 14
view all 5 authors...
There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general consensus over what is meant by ‘explainable’ and ‘interpretable’. In this paper, we argue that this lack of consensus is due to there being several distinct stakeholder communities. We note that, while the concerns of the individual communities are broadly compatible, they are not identical, which gives rise to differe...
7 Citations
#1Federico Cerutti (Cardiff University)H-Index: 12
#2Moustafa Alzantot (UCLA: University of California, Los Angeles)H-Index: 10
Last. Mani Srivastava (UCLA: University of California, Los Angeles)H-Index: 91
view all 13 authors...
In this paper we provide a critical analysis with metrics that will inform guidelines for designing distributed systems for Collective Situational Understanding (CSU). CSU requires both collective insight-i.e., accurate and deep understanding of a situation derived from uncertain and often sparse data and collective foresight-i.e., the ability to predict what will happen in the future. When it comes to complex scenarios, the need for a distributed CSU naturally emerges, as a single monolithic ap...
1 CitationsSource
1234567