Sumit Kumar Jha
YOU?
Author Swipe
View article: DML-RAM: Deep Multimodal Learning Framework for Robotic Arm Manipulation using Pre-trained Models
DML-RAM: Deep Multimodal Learning Framework for Robotic Arm Manipulation using Pre-trained Models Open
This paper presents a novel deep learning framework for robotic arm manipulation that integrates multimodal inputs using a late-fusion strategy. Unlike traditional end-to-end or reinforcement learning approaches, our method processes image…
View article: Filtering Online Harassment: ML based Cyberbullying Detectionz
Filtering Online Harassment: ML based Cyberbullying Detectionz Open
Cyber bullying has emerged as a great threat to the people on the internet. The platform, which was made for good use, is being used by some to harass people. This is actually a misuse of a great invention. Also, the nature of social media…
View article: Elucidating the Fracture Toughness of Additively Manufactured and Thermo-Mechanically Treated Ti6Al4V
Elucidating the Fracture Toughness of Additively Manufactured and Thermo-Mechanically Treated Ti6Al4V Open
View article: LOGIC: Logic Synthesis for Digital In-Memory Computing
LOGIC: Logic Synthesis for Digital In-Memory Computing Open
In-memory processing offers a promising solution for enhancing the performance of data-intensive applications. While analog in-memory computing demonstrates remarkable efficiency, its limited precision is suitable only for approximate comp…
View article: Energy spectra and fluxes of two-dimensional turbulent quantum droplets
Energy spectra and fluxes of two-dimensional turbulent quantum droplets Open
We explore the energy spectra and associated fluxes of turbulent two-dimensional quantum droplets subjected to a rotating paddling potential which is removed after a few oscillation periods. A systematic analysis on the impact of the chara…
View article: Empowering Student Success: A Comprehensive Task Management and Notification System
Empowering Student Success: A Comprehensive Task Management and Notification System Open
View article: James: Enhancing Judicial Efficiency with Smart Administration
James: Enhancing Judicial Efficiency with Smart Administration Open
View article: Equivalence Checking for Flow-Based Computing using Iterative SAT Solving
Equivalence Checking for Flow-Based Computing using Iterative SAT Solving Open
View article: SATYA: Defending Against Adversarial Attacks Using Statistical HypothesisTesting
SATYA: Defending Against Adversarial Attacks Using Statistical HypothesisTesting Open
The paper presents a new defense against adversarial attacks for deep neural networks. We demonstrate the effectiveness of our approach against the popular adversarial image generation method DeepFool. Our approach uses Wald’s Sequential P…
View article: Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations
Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations Open
Signal analysis and classification is fraught with high levels of noise and perturbation. Computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, t…
View article: Jailbreaking Large Language Models with Symbolic Mathematics
Jailbreaking Large Language Models with Symbolic Mathematics Open
Recent advancements in AI safety have led to increased efforts in training and red-teaming large language models (LLMs) to mitigate unsafe content generation. However, these safety mechanisms may not be comprehensive, leaving potential vul…
View article: AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing
AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz Testing Open
Recent advancements in automatic code generation using large language models (LLMs) have brought us closer to fully automated secure software development. However, existing approaches often rely on a single agent for code generation, which…
View article: NSP: A Neuro-Symbolic Natural Language Navigational Planner
NSP: A Neuro-Symbolic Natural Language Navigational Planner Open
Path planners that can interpret free-form natural language instructions hold promise to automate a wide range of robotics applications. These planners simplify user interactions and enable intuitive control over complex semi-autonomous sy…
View article: Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations
Improving Robustness of Spectrogram Classifiers with Neural Stochastic Differential Equations Open
Signal analysis and classification is fraught with high levels of noise and perturbation. Computer-vision-based deep learning models applied to spectrograms have proven useful in the field of signal classification and detection; however, t…
View article: Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma
Development and Validation of Fully Automatic Deep Learning-Based Algorithms for Immunohistochemistry Reporting of Invasive Breast Ductal Carcinoma Open
Immunohistochemistry (IHC) analysis is a well-accepted and widely used method for molecular subtyping, a procedure for prognosis and targeted therapy of breast carcinoma, the most common type of tumor affecting women. There are four molecu…
View article: Multi-Stain Multi-Level Convolutional Network for Multi-Tissue Breast Cancer Image Segmentation
Multi-Stain Multi-Level Convolutional Network for Multi-Tissue Breast Cancer Image Segmentation Open
Digital pathology and microscopy image analysis are widely employed in the segmentation of digitally scanned IHC slides, primarily to identify cancer and pinpoint regions of interest (ROI) indicative of tumor presence. However, current ROI…
View article: Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks
Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks Open
Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as membership inference attacks (MIA). Existing works have onl…
View article: Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision
Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision Open
Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong axiomatic foundation. The algorithm is based on integrating …
View article: Multi-Stain Multi-Level Convolutional Network for Multi-Tissue breast cancer image segmentation
Multi-Stain Multi-Level Convolutional Network for Multi-Tissue breast cancer image segmentation Open
Digital pathology and microscopy image analysis are widely employed in the segmentation of digitally scanned IHC slides, primarily to identify cancer and pinpoint regions of interest (ROI) indicative of tumor presence. However, current ROI…
View article: Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning
Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning Open
Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is pro…
View article: Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving
Neuro Symbolic Reasoning for Planning: Counterexample Guided Inductive Synthesis using Large Language Models and Satisfiability Solving Open
Generative large language models (LLMs) with instruct training such as GPT-4 can follow human-provided instruction prompts and generate human-like responses to these prompts. Apart from natural language responses, they have also been found…
View article: Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions
Neural Stochastic Differential Equations for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions Open
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 Equat…
View article: Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision
Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision Open
Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong axiomatic foundation. The algorithm is based on integrating …
View article: quTARANG: A python GPE solver to study turbulence in quantum systems
quTARANG: A python GPE solver to study turbulence in quantum systems Open
quTARANG is a Python-based general-purpose Gross-Pitaevskii Equation (GPE) solver. It can solve GPE in 1D, 2D and 3D and has the ability to run on both CPU and GPU. It has been developed to study turbulence in quantum systems, specifically…
View article: On the Robustness of AlphaFold: A COVID-19 Case Study
On the Robustness of AlphaFold: A COVID-19 Case Study Open
Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been explored. This is particularly rele…
View article: FAT-PIM: Low-Cost Error Detection for Processing-In-Memory
FAT-PIM: Low-Cost Error Detection for Processing-In-Memory Open
Processing In Memory (PIM) accelerators are promising architecture that can provide massive parallelization and high efficiency in various applications. Such architectures can instantaneously provide ultra-fast operation over extensive dat…
View article: ExplainIt!: A Tool for Computing Robust Attributions of DNNs
ExplainIt!: A Tool for Computing Robust Attributions of DNNs Open
Responsible integration of deep neural networks into the design of trustworthy systems requires the ability to explain decisions made by these models. Explainability and transparency are critical for system analysis, certification, and hum…
View article: Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations
Shaping Noise for Robust Attributions in Neural Stochastic Differential Equations Open
Neural SDEs with Brownian motion as noise lead to smoother attributions than traditional ResNets. Various attribution methods such as saliency maps, integrated gradients, DeepSHAP and DeepLIFT have been shown to be more robust for neural S…
View article: A Game-theoretic Understanding of Repeated Explanations in ML Models
A Game-theoretic Understanding of Repeated Explanations in ML Models Open
This paper formally models the strategic repeated interactions between a system, comprising of a machine learning (ML) model and associated explanation method, and an end-user who is seeking a prediction/label and its explanation for a que…
View article: Two complementary relations for the Rogers-Ramanujan continued fraction
Two complementary relations for the Rogers-Ramanujan continued fraction Open
Let $R(q)$ be the Rogers-Ramanujan continued fraction. We give different proofs of two complementary relations for $R(q)$ given by Ramanujan and proved by Watson and Ramanathan. Our proofs only use product expansions for classical Jacobi t…