KISP Lab

About Us

We do research in the domain of the security and privacy of computers and communications at the National University of Singapore (School of Computing). Our research spans the following themes: ML Security, Decentralized Systems Security, Security Processors, and Automatic Program Translation. Our motto is “Keep It Secure and Private” or KISP for short.

Projects

Capstone

Capability-based Architectural Foundation for Expressive Security

How can the computer architecture provide principled and provable support for diverse software security needs? Capstone provides an answer!

APT

Automated Program Translation

Wondering how to translate your program from one language to another? APT is here to help!

MAPS

Machine Learning and Algorithms for Practical Security

Trying to solve ML security problems once and for all? MAPS is here to help!

Publications

• Anvil: A General-Purpose Timing-Safe Hardware Description Language

  Jason Zhijingcheng Yu*, Aditya Ranjan Jha*, Umang Mathur, Trevor E. Carlson, Prateek Saxena

  ASPLOS 2026 · Pittsburgh, PA, USA · March 2026

  PDF Artefact Playground Docs

• Model Provenance Testing for Large Language Models

  Ivica Nikolic, Teodora Baluta, Prateek Saxena

  NeurIPS 2025 · San Diego, California, USA · December 2025

  PDF Artefact

• Securing Mixed Rust with Hardware Capabilities

  Jason Zhijingcheng Yu*, Fangqi Han*, Kaustab Choudhary, Trevor E. Carlson, Prateek Saxena

  CCS 2025 · Taipei, Taiwan · October 2025

  PDF Artefact

• A Practical and Secure Byzantine Robust Aggregator

  De Zhang Lee, Aashish Kolluri, Prateek Saxena, Ee-Chien Chang

  CCS 2025 · Taipei, Taiwan · October 2025

  PDF Artefact

• Caplification: Bridging Capability-Aware and Capability-Oblivious Software

  Jason Zhijingcheng Yu, Mingkai Li, Aditya Badole, Trevor E. Carlson, Michael Swift, Prateek Saxena

  SACMAT 2025 · Stony Brook, New York, USA · July 2025

  PDF Artefact

• Program Skeletons for Automated Program Translation

  Bo Wang*, Tianyu Li*, Ruishi Li, Umang Mathur, Prateek Saxena

  PLDI 2025 · Seoul, South Korea · June 2025

  PDF Artefact

• Translating C To Rust: Lessons from a User Study

  Ruishi Li*, Bo Wang*, Tianyu Li, Prateek Saxena, Ashish Kundu

  NDSS 2025 · San Diego, CA · February 2025

  PDF Benchmark

• Attacking Byzantine Robust Aggregation in High Dimensions

  Sarthak Choudhary*, Aashish Kolluri*, Prateek Saxena

  S&P OAKLAND 2024 · Oakland, CA · May 2024

  PDF Artefact

• Unforgeability in Stochastic Gradient Descent

  Teodora Baluta, Ivica Nikolic, Racchit Jain, Divesh Aggarwal, Prateek Saxena

  CCS 2023 · Copenhagen, DK · Nov 2023

  PDF Artefact

• TransMap: Pinpointing Mistakes in Neural Code Translation

  Bo Wang, Ruishi Li, Mingkai Li, Prateek Saxena

  ESEC/FSE 2023 · San Francisco, CA · Dec 2024

  PDF Artefact

• Capstone: A Capability-based Foundation for Trustless Secure Memory Access

  Jason Zhijingcheng Yu, Conrad Watt, Aditya Badole, Trevor Carlson, Prateek Saxena

  Usenix Security 2023 · Anaheim , CA · Aug 2023

  PDF Artefact

• User-customizable Transpilation for Scripting Languages

  Bo Wang, Aashish Kolluri, Ivica Nikolic, Teodora Baluta, Prateek Saxena

  OOPSLA 2023 · Cascais, PT · Oct 2023

  PDF Artefact