About Me

Hello! I am Meet Udeshi. Since Sept. 2022, I am a PhD student at NYU Tandon where I am advised by Prof. Farshad Khorrami and Prof. Ramesh Karri in the Control/Robotics Research Lab (CRRL) and the Center for Cybersecurity. My research focus is on the security of cyber-physical systems and embedded systems. My interests include hardware security, firmware binary analysis, reverse engineering, and applications of LLMs to cybersecurity.

Previously, I was a senior engineer at Qualcomm Bengaluru in the ML Compiler Team. I worked on the compiler stack for the Cloud AI100 Accelerator platform. I completed my Bachelor’s and Master’s degree in Electrical Engineering from IIT Bombay (Mumbai, India) in 2019. My Master’s was focused on hardware security, as part of Computer Architecture and Dependable Systems Lab (CADSL) guided by Prof. Virendra Singh. For my thesis, I designed a denial-of-service attack for the memory prefetcher.

I am an avid reader of manga and novels. I love sketching, gardening, brewing tea and coffee in my free time. I keep publishing hobby projects on github, you can find a (rarely updated) list on the projects page.

Selected Publications

1. Meet Udeshi, Prashanth Krishnamurthy, Hammond Pearce, Ramesh Karri, and Farshad Khorrami. REMaQE: Reverse Engineering Math Equations from Executables. 2024. ACM Transactions on Cyber-Physical Systems. [doi] [pdf].
2. Meet Udeshi, Prashanth Krishnamurthy, Hammond Pearce, Ramesh Karri, and Farshad Khorrami. REMEND: Neural Decompilation for Reverse Engineering Math Equations from Binary Executables. 2025. ACM Transactions on Intelligent Systems and Technology. [doi].
3. Talor Abramovich, Meet Udeshi*, Minghao Shao*, Kilian Lieret, Haoran Xi, Kimberly Milner, Sofija Jancheska, John Yang, Carlos E. Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik Narasimhan, Ramesh Karri, Ofir Press. EnIGMA: Enhanced Interactive Generative Model Agent for CTF Challenges. 2025. International Conference on Machine Learning (ICML). [openreview] [pdf].
4. Minghao Shao*, Sofija Jancheska*, Meet Udeshi*, Brendan Dolan-Gavitt*, Haoran Xi, Kimberly Milner, Boyuan Chen, Max Yin, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Muhammad Shafique. NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security. 2024. Neural Information Processing Systems (NeurIPS). [openreview] [pdf], [poster].
5. Meet Udeshi, Prashanth Krishnamurthy, Ramesh Karri and Farshad Khorrami. Tamper-Proof Network Traffic Measurements on a NIC for Intrusion Detection. 2024. IEEE Transactions on Network and Service Management, [doi].

For the full list, see my google scholar.

Featured Projects

Cybersecurity LLM Agents for solving CTF Challenges

Developing LLM cybersecurity capabilities is important as LLMs are very useful in automating cybersecurity analysis with their vast breadth of knowledge. I worked on building the NYU CTF Bench dataset of CTF challenges to test LLM cybersecurity capabilities. I also worked on the EnIGMA agent with interactive agent tools and enhanced agent-computer interface.

Tamper-Proof Network Traffic Measurements on a NIC for Intrusion Detection

I have developed a framework that leverages the network interface card (NIC) to collect tamper-proof network traffic measurements for intrusion detection systems. Rootkits that compromise the host OS can tamper host-side network measurements but cannot easily touch peripherals that operate outside the host OS domain, such as the NIC. The framework can collect reliably accurate measurements with negligible impact to network performance.

Reverse Engineering Math Equations from Binaries -- Symbolic and Neural Approaches

Reverse engineering math equations from binaries of embedded systems is immensely useful to analyze the implemented mathematical models for security purposes. I have developed two frameworks for reverse engineering math equations -- REMaQE, an automated dynamic analysis framework utilizing symbolic execution; and REMEND, a neural decompilation framework with enhanced disassembler for extracting math equations using single pass static analysis.