51 citations · 153 across the 19 of their papers we have counts for
19 papers
Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning
Rakshit Naidu
Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems. Prior work has shown that DP-SGD can widen accuracy disparities a…
Fair Finetuning Mitigates Distribution Inference Attacks
Rakshit Naidu
Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat known as distribution inference…
Personalized Differential Privacy for Ridge Regression
Krishna Acharya, Franziska Boenisch, Rakshit Naidu +1
The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requ…
Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Tools
Emily Black, Rakshit Naidu, Rayid Ghani +3
While algorithmic fairness is a thriving area of research, in practice, mitigating issues of bias often gets reduced to enforcing an arbitrarily chosen fairness metric, either by e…
Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization
Aman Priyanshu, Supriti Vijay, Ayush Kumar +2
LLM-powered chatbots are becoming widely adopted in applications such as healthcare, personal assistants, industry hiring decisions, etc. In many of these cases, chatbots are fed s…
Fair Context-Aware Privacy Threat Modelling
Saswat Das, Rakshit Naidu
Given the progressive nature of the world today, fairness is a very important social aspect in various areas, and it has long been studied with the advent of technology. To the bes…
Can Causal (and Counterfactual) Reasoning improve Privacy Threat Modelling?
Rakshit Naidu, Navid Kagalwalla
Causal questions often permeate in our day-to-day activities. With causal reasoning and counterfactual intuition, privacy threats can not only be alleviated but also prevented. In…
Pruning has a disparate impact on model accuracy
Cuong Tran, Ferdinando Fioretto, Jung-Eun Kim +1
Network pruning is a widely-used compression technique that is able to significantly scale down overparameterized models with minimal loss of accuracy. This paper shows that prunin…
Interpretability of Fine-grained Classification of Sadness and Depression
Tiasa Singha Roy, Priyam Basu, Aman Priyanshu +1
While sadness is a human emotion that people experience at certain times throughout their lives, inflicting them with emotional disappointment and pain, depression is a longer term…
Privacy enabled Financial Text Classification using Differential Privacy and Federated Learning
Priyam Basu, Tiasa Singha Roy, Rakshit Naidu +1
Privacy is important considering the financial Domain as such data is highly confidential and sensitive. Natural Language Processing (NLP) techniques can be applied for text classi…
Efficient Hyperparameter Optimization for Differentially Private Deep Learning
Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah +1
Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used man…
Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
Rakshit Naidu, Harshita Diddee, Ajinkya Mulay +3
In recent years, machine learning techniques utilizing large-scale datasets have achieved remarkable performance. Differential privacy, by means of adding noise, provides strong pr…
When Differential Privacy Meets Interpretability: A Case Study
Rakshit Naidu, Aman Priyanshu, Aadith Kumar +3
Given the increase in the use of personal data for training Deep Neural Networks (DNNs) in tasks such as medical imaging and diagnosis, differentially private training of DNNs is s…
Benchmarking Differential Privacy and Federated Learning for BERT Models
Priyam Basu, Tiasa Singha Roy, Rakshit Naidu +3
Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depres…
DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?
Archit Uniyal, Rakshit Naidu, Sasikanth Kotti +4
Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on dif…
FedPandemic: A Cross-Device Federated Learning Approach Towards Elementary Prognosis of Diseases During a Pandemic
Aman Priyanshu, Rakshit Naidu
The amount of data, manpower and capital required to understand, evaluate and agree on a group of symptoms for the elementary prognosis of pandemic diseases is enormous. In this pa…
IS-CAM: Integrated Score-CAM for axiomatic-based explanations
Rakshit Naidu, Ankita Ghosh, Yash Maurya +2
Convolutional Neural Networks have been known as black-box models as humans cannot interpret their inner functionalities. With an attempt to make CNNs more interpretable and trustw…
TeleVital: Enhancing the quality of contactless health assessment
Jithin Sunny, Joel Jogy, Rohan Rout +1
In the midst of rising positive cases of COVID-19, the hospitals face a newfound difficulty to prioritize on their patients and accommodate them. Moreover, crowding of patients at…
SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization
Haofan Wang, Rakshit Naidu, Joy Michael +1
Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications…