Search Results for author: Soham Pal

Found 4 papers, 3 papers with code

Stateful Detection of Model Extraction Attacks

1 code implementation12 Jul 2021 Soham Pal, Yash Gupta, Aditya Kanade, Shirish Shevade

Machine-Learning-as-a-Service providers expose machine learning (ML) models through application programming interfaces (APIs) to developers.

BIG-bench Machine Learning Model extraction

ACTIVETHIEF: Model Extraction Using Active Learning and Unannotated Public Data

1 code implementation7 Feb 2020 Soham Pal, Yash Gupta, Aditya Shukla, Aditya Kanade, Shirish Shevade, Vinod Ganapathy

We demonstrate that (1) it is possible to use ACTIVETHIEF to extract deep classifiers trained on a variety of datasets from image and text domains, while querying the model with as few as 10-30% of samples from public datasets, (2) the resulting model exhibits a higher transferability success rate of adversarial examples than prior work, and (3) the attack evades detection by the state-of-the-art model extraction detection method, PRADA.

Active Learning BIG-bench Machine Learning +1

DeepFix: Fixing Common C Language Errors by Deep Learning

1 code implementation4 Feb 2017 Rahul Gupta, Soham Pal, Aditya Kanade, Shirish Shevade

The problem of automatically fixing programming errors is a very active research topic in software engineering.

Program Repair

Cannot find the paper you are looking for? You can Submit a new open access paper.