Pratik Vaishnavi

Pratik Vaishnavi

Contact
E-mailE-Mail Google ScholarGoogle Scholar GitHubGitHub LinkedInLinkedIn

About Me

Welcome to my homepage! My name is Pratik and I'm a PhD Candidate in the Computer Science Department at Stony Brook University. I'm a member of the Ethos Security and Privacy Lab, led by Amir Rahmati where we tackle the security and privacy challenges of emerging technologies (including IoT, AR, and ML systems).

The objective of my research is to make secure machine learning accessible to everyone. Currently, I'm focused on developing efficient methods for training empirically and provably robust neural networks, collaborating closely with Kevin Eykholt from IBM Research.

In addition to my academic journey, I've had the privilege of applying my research skills in practical settings. As a Security and Privacy Research Intern at Sony AI (Summer '23), I developed efficient robustness learning methods to reduce the financial cost and environmental impact of training robust ML models for commercial applications. I also contributed towards enhancing the robustness of the Amazon One device during my Applied Scientist Internships at Amazon (Summer '20 & '21).

Before embarking on my PhD journey, I earned a MS degree in Computer Science from Stony Brook University in 2018. My MS Thesis focused on generating temporal action proposals in long untrimmed videos. My academic journey started with a Bachelor's degree in Electronics Engineering from Sardar Vallabhbhai National Institute of Technology, Surat, India, which I completed in 2016.

Outside of my academic pursuits, you'll find me immersed in a good book, exploring the waters via kayaking, or enjoying some downtime with video games (big FromSoft fan!). Thanks for visiting!


News

Jan '24 Serving as reviewer for ECCV and ACCV 2024.
Dec '23 Serving as reviewer for ICML 2024.
Oct '23 Serving as reviewer for CVPR 2024.
Sep '23 Serving as reviewer for IEEE S&P and ICLR 2024.
May '23 Joining Sony AI (Tokyo) as intern in the Privacy Preserving ML team for 3 months!
Mar '23 Serving as a reviewer for ICCV and NeurIPS 2023.
Feb '23 Passed my PhD dissertation proposal! Will do the final defense in Dec '23 (tentatively).
Dec '22 Presenting two papers at NeurIPS 2022 in New Orleans, LA!
Oct '22 Serving as a reviewer for CVPR 2023.
Oct '22 Won the Best Overall Poster award at the Graduate Research Day held in my department!
Oct '22 Our preliminary work on the feasibility of compressing certifiably robust neural networks was accepted at NeurIPS 2022 workshop on Trustworthy and Socially Responsible ML!
Sept '22 Our paper on accelerating the process of training certifiably robust neural networks was accepted at NeurIPS 2022!
Aug '22 Presenting our paper on accelerating adversarial training at USENIX Security 2022 in Boston, MA.

Publications

  • On the Feasibility of Compressing Certifiably Robust Neural Networks
    Pratik Vaishnavi, Veena Krish, Farhan Ahmed, Kevin Eykholt, Amir Rahmati
    NeurIPS 2022, Workshop on Trustworthy and Socially Responsible ML
    venue

  • Accelerating Certified Robustness Training via Knowledge Transfer
    Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati
    NeurIPS 2022
    PDF code venue

  • Ares: A System-Oriented Wargame Framework for Adversarial ML
    Farhan Ahmed, Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati
    IEEE S&P 2022, Workshop on Deep Learning Security
    PDF code venue

  • Transferring Adversarial Robustness Through Robust Representation Matching
    Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati
    USENIX Security 2022
    PDF code video venue

  • Can Attention Masks Improve Adversarial Robustness?
    Pratik Vaishnavi, Tianji Cong, Kevin Eykholt, Atul Prakash, Amir Rahmati
    AAAI 2020, Workshop on Engineering Dependable and Secure ML Systems
    PDF venue

  • Robust Pose Recognition Using Deep Learning
    Aparna Mohanty, Alfaz Ahmed, Trishita Goswami, Arpita Das, Pratik Vaishnavi, Rajiv Ranjan Sahay
    CVIP 2016
    PDF venue

  • Nrityabodha: Towards Understanding Indian Classical Dance Using a Deep Learning Approach
    Aparna Mohanty, Pratik Vaishnavi, Prerana Jana, Anubhab Majumdar, Alfaz Ahmed, Trishita Goswami, Rajiv Ranjan Sahay
    Signal Processing: Image Communication 2016
    PDF venue


Hosted on GitHub Pages — Theme by orderedlist