Is Watermarking LLM-Generated Code Robust?

1 code implementation • 24 Mar 2024 • Tarun Suresh, Shubham Ugare, Gagandeep Singh, Sasa Misailovic

We present the first study of the robustness of existing watermarking techniques on Python code generated by large language models.

SynCode: LLM Generation with Grammar Augmentation

1 code implementation • 3 Mar 2024 • Shubham Ugare, Tarun Suresh, Hangoo Kang, Sasa Misailovic, Gagandeep Singh

LLMs are widely used in complex AI applications.

Code Generation valid

Incremental Randomized Smoothing Certification

1 code implementation • 31 May 2023 • Shubham Ugare, Tarun Suresh, Debangshu Banerjee, Gagandeep Singh, Sasa Misailovic

We experimentally demonstrate the effectiveness of our approach, showing up to 3x certification speedup over the certification that applies randomized smoothing of the approximate model from scratch.

Incremental Verification of Neural Networks

2 code implementations • 4 Apr 2023 • Shubham Ugare, Debangshu Banerjee, Sasa Misailovic, Gagandeep Singh

Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e. g., robustness, fairness) on an infinite set of inputs or not.

Fairness

Secure Medical Image Analysis with CrypTFlow

1 code implementation • 9 Dec 2020 • Javier Alvarez-Valle, Pratik Bhatu, Nishanth Chandran, Divya Gupta, Aditya Nori, Aseem Rastogi, Mayank Rathee, Rahul Sharma, Shubham Ugare

Our first component is an end-to-end compiler from TensorFlow to a variety of MPC protocols.

Cryptography and Security