Fetching the paper…
Reading the bibliography…
We present a comprehensive evaluation of the robustness and explainability of ResNet-like models in the context of Unintended Radiated Emission (URE) classification and suggest a new approach leveraging Neural Stochastic Differential Equations (SDEs) to address identified limitations.
Imagenet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei · 2009
Earlier work this paper cites.
Towards automated system synthesis using sciduction
Susmit Kumar Jha · 2011
Earlier work this paper cites.
On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation
Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek · 2015
Earlier work this paper cites.
On learning optimized reaction diffusion processes for effective image restoration
Yunjin Chen, Wei Yu, and Thomas Pock · 2015
Earlier work this paper cites.
Parallel boolean matrix multiplication in linear time using rectifying memristors
Alvaro Velasquez and Sumit Kumar Jha · 2016
Earlier work this paper cites.
Multi-level residual networks from dynamical systems view
Bo Chang, Lili Meng, Eldad Haber, Frederick Tung, and David Begert · 2017
Earlier work this paper cites.
A unified approach to interpreting model predictions
Scott M Lundberg and Su-In Lee · 2017
Earlier work this paper cites.
Grad-cam: Visual explanations from deep networks via gradient-based localization
Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra · 2017
Earlier work this paper cites.
Double continuum limit of deep neural networks
Sho Sonoda and Noboru Murata · 2017
Earlier work this paper cites.
Smoothgrad: removing noise by adding noise
Daniel Smilkov, Nikhil Thorat, Been Kim, Fernanda Viégas, and Martin Wattenberg · 2017
Earlier work this paper cites.
Axiomatic attribution for deep networks
Mukund Sundararajan, Ankur Taly, and Qiqi Yan · 2017
Cited alongside, same era.
A dimensionally aligned signal projection for classification of unintended radiated emissions
Jason Michael Vann, Thomas P Karnowski, Ryan Kerekes, Corey D Cooke, and Adam L Anderson · 2017
Cited alongside, same era.
Neural ordinary differential equations
Ricky TQ Chen, Yulia Rubanova, Jesse Bettencourt, and David K Duvenaud · 2018
Cited alongside, same era.
Free binary decision diagram-based synthesis of compact crossbars for in-memory computing
Amad Ul Hassen, Dwaipayan Chakraborty, and Sumit Kumar Jha · 2018
Cited alongside, same era.
Detecting adversarial examples using data manifolds
Susmit Jha, Uyeong Jang, Somesh Jha, and Brian Jalaian · 2018
Cited alongside, same era.
Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations
Model-centered assurance for autonomous systems
Susmit Jha, John Rushby, and Natarajan Shankar · 2020
Later among the works it cites.
How does noise help robustness? explanation and exploration under the neural sde framework
Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, and Cho-Jui Hsieh · 2020
Later among the works it cites.
Design and fabrication of flow-based edge detection memristor crossbar circuits
Jodh Singh Pannu, Sunny Raj, Steven Lawrence Fernandes, Dwaipayan Chakraborty, Sarah Rafiq, Nathaniel Cady, and Sumit Kumar Jha · 2020
Later among the works it cites.
On smoother attributions using neural stochastic differential equations
Sumit Jha, Rickard Ewetz, Alvaro Velasquez, and Susmit Jha · 2021
Later among the works it cites.
Protein folding neural networks are not robust
Sumit Kumar Jha, Arvind Ramanathan, Rickard Ewetz, Alvaro Velasquez, and Susmit Jha · 2021
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Yiping Lu, Aoxiao Zhong, Quanzheng Li, and Bin Dong · 2018
Cited alongside, same era.
Attribution-based confidence metric for deep neural networks
Susmit Jha, Sunny Raj, Steven Fernandes, Sumit K Jha, Somesh Jha, Brian Jalaian, Gunjan Verma, and Ananthram Swami · 2019
Cited alongside, same era.
Attribution-driven causal analysis for detection of adversarial examples
Susmit Jha, Sunny Raj, Steven Lawrence Fernandes, Sumit Kumar Jha, Somesh Jha, Gunjan Verma, Brian Jalaian, and Ananthram Swami · 2019
Cited alongside, same era.
Explanation of unintended radiated emission classification via lime
Tom Grimes, Eric Church, William Pitts, and Lynn Wood · 2020
Cited alongside, same era.
Liam Hodgkinson, Chris van der Heide, Fred Roosta, and Michael W Mahoney · 2020
Cited alongside, same era.
Flaming moe
Tom Karnowski, Ryan Kerekes, Corey Cooke, Michael Vann, Mark Adams, and Philip Bingham · 2021
Later among the works it cites.
Shaping noise for robust attributions in neural stochastic differential equations
Sumit Kumar Jha, Rickard Ewetz, Alvaro Velasquez, Arvind Ramanathan, and Susmit Jha · 2022
Later among the works it cites.
Explainit!: A tool for computing robust attributions of dnns
Sumit Jha, Alvaro Velasquez, Rickard Ewetz, Laura Pullum, and Susmit Jha · 2022
Later among the works it cites.
idecode: In-distribution equivariance for conformal out-of-distribution detection
Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Edgar Dobriban, Oleg Sokolsky, and Insup Lee · 2022
Later among the works it cites.
A survey on the vulnerability of deep neural networks against adversarial attacks
Andy Michel, Sumit Kumar Jha, and Rickard Ewetz · 2022
Later among the works it cites.