no code implementations • 11 Oct 2024 • Zain Sarwar, Van Tran, Arjun Nitin Bhagoji, Nick Feamster, Ben Y. Zhao, Supriyo Chakraborty
Machine learning (ML) models often require large amounts of data to perform well.
no code implementations • 19 Sep 2024 • Akshaj Kumar Veldanda, Shi-Xiong Zhang, Anirban Das, Supriyo Chakraborty, Stephen Rawls, Sambit Sahu, Milind Naphade
Large language models (LLMs) have revolutionized various domains, yet their utility comes with significant challenges related to outdated or problematic knowledge embedded during pretraining.
1 code implementation • 20 Aug 2024 • Sanjay Bhargav Dharavath, Tanmoy Dam, Supriyo Chakraborty, Prithwiraj Roy, Aniruddha Maiti
The field of autonomous vehicles (AVs) predominantly leverages multi-modal integration of LiDAR and camera data to achieve better performance compared to using a single modality.
1 code implementation • 12 Feb 2024 • Tanmoy Dam, Sanjay Bhargav Dharavath, Sameer Alam, Nimrod Lilith, Supriyo Chakraborty, Mir Feroskhan
Combining LiDAR and camera data has shown potential in enhancing short-distance object detection in autonomous driving systems.
1 code implementation • 9 Jan 2024 • Supriyo Chakraborty, Aurobinda Routray, Sanjay Bhargav Dharavath, Tanmoy Dam
However, the detection of sparse thin layers within seismic datasets presents a significant challenge due to the ill-posed nature and poor non-linearity of the problem.
no code implementations • 19 Oct 2023 • Cai Davies, Marc Roig Vilamala, Alun D. Preece, Federico Cerutti, Lance M. Kaplan, Supriyo Chakraborty
In this paper, we empirically investigate the correlations between misclassification and evaluated uncertainty, and show that EDL's `evidential signal' is due to misclassification bias.
no code implementations • 28 Jun 2022 • Pengrui Quan, Supriyo Chakraborty, Jeya Vikranth Jeyakumar, Mani Srivastava
A variety of explanation methods have been proposed in recent years to help users gain insights into the results returned by neural networks, which are otherwise complex and opaque black-boxes.
1 code implementation • 12 Dec 2021 • Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji, Supriyo Chakraborty, Prateek Mittal
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices.
no code implementations • 1 Mar 2021 • Devansh Shah, Parijat Dube, Supriyo Chakraborty, Ashish Verma
We observe a significant drop in both natural and adversarial accuracies when AT is used in the federated setting as opposed to centralized training.
1 code implementation • 22 Jul 2020 • Heiko Ludwig, Nathalie Baracaldo, Gegi Thomas, Yi Zhou, Ali Anwar, Shashank Rajamoni, Yuya Ong, Jayaram Radhakrishnan, Ashish Verma, Mathieu Sinn, Mark Purcell, Ambrish Rawat, Tran Minh, Naoise Holohan, Supriyo Chakraborty, Shalisha Whitherspoon, Dean Steuer, Laura Wynter, Hifaz Hassan, Sean Laguna, Mikhail Yurochkin, Mayank Agarwal, Ebube Chuba, Annie Abay
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
no code implementations • 31 Mar 2020 • Liam Hiley, Alun Preece, Yulia Hicks, Supriyo Chakraborty, Prudhvi Gurram, Richard Tomsett
Our results show that the selective relevance method can not only provide insight on the role played by motion in the model's decision -- in effect, revealing and quantifying the model's spatial bias -- but the method also simplifies the resulting explanations for human consumption.
no code implementations • 18 Mar 2020 • Chawin Sitawarin, Supriyo Chakraborty, David Wagner
This leads to a significant improvement in both clean accuracy and robustness compared to AT, TRADES, and other baselines.
no code implementations • 29 Nov 2019 • Richard Tomsett, Dan Harborne, Supriyo Chakraborty, Prudhvi Gurram, Alun Preece
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").
2 code implementations • ICLR 2019 • Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, Seraphin Calo
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.
no code implementations • 29 Sep 2018 • Alun Preece, Dan Harborne, Dave Braines, Richard Tomsett, Supriyo Chakraborty
There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable.
no code implementations • 20 Jun 2018 • Richard Tomsett, Dave Braines, Dan Harborne, Alun Preece, Supriyo Chakraborty
Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
3 code implementations • 28 May 2018 • Moustafa Alzantot, Yash Sharma, Supriyo Chakraborty, huan zhang, Cho-Jui Hsieh, Mani Srivastava
Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches.
no code implementations • 31 Jan 2017 • Moustafa Alzantot, Supriyo Chakraborty, Mani B. Srivastava
second, we use another LSTM network based discriminator model for distinguishing between the true and the synthesized data.
no code implementations • 9 Dec 2015 • Jorge Ortiz, Chien-chin Huang, Supriyo Chakraborty
In this paper, we show that by combining the computing power distributed over a number of phones, judicious optimization choices, and contextual information it is possible to execute the end-to-end pipeline entirely on the phones at the edge of the network, efficiently.