I am a PhD Candidate at Columbia University, where I work in the Security Group under Professors Suman Jana and Salvatore Stolfo. I am generally interested in Deep Learning based approaches to Program Analysis and Synthesis.


AWS A.I. Labs 2023. Internship with AWS A.I. Labs advised by visiting Prof. Baishahki Ray on using Large Language Models for regression testing software. Developed novel approach to LLM test generation using static analysis to prompt the model to reason symbolically about program execution paths. Achieved improvements of $2\times$ coverage and $3\times$ correct test generations over baselines when evaluated on CodeGen2 and OpenAI GPT-3.5 and GPT-4 models.

Microsoft Research 2021. Internship with Microsoft Research RiSE group advised by Sr. Principal Researchers Todd Mytkowitz and Shuvendu Lahiri. Developed TOGA: A Neural Method for Test Oracle Generation using neural transformers and a specialized grammar to automatically generate unit tests that are highly effective at finding bugs (170% improvement over any other evaluated system). Published in ICSE 2022 and awarded ACM Sigsoft Distinguished Paper Award: paper.


[Oakland S&P 2023] Precise Detection of Kernel Data Races with Probabilistic Lockset Analysis. Gabriel Ryan, Abhishek Shah, Dongdong She, Suman Jana. [paper]

[ICSE 2022] TOGA: A Neural Method for Test Oracle Generation. Elizabeth Dinella*, Gabriel Ryan*, Todd Mytokowitz, Shuvendu Lahiri. [paper] [code] (ACM Sigsoft Distinguished Paper Award)

[OSDI 2021] DistAI: Data-Driven Automated Invariant Learning for Distributed Protocols. Jianan Yao, Runzhou Tao, Ronghui Gu, Jason Nieh, Suman Jana, Gabriel Ryan. [paper] [code] (OSDI Jay Lepreau Best Paper Award)

[USENIX Security 2021] Fine Grained Dataflow Tracking with Proximal Gradients. Gabriel Ryan, Abhishek Shah, Dongdong She, Koustubha Bhat, and Suman Jana. [paper] [code]

[PLDI 2020] Learning Nonlinear Loop Invariants with Gated Continuous Logic Networks. Jianan Yao*, Gabriel Ryan*, Justin Wong*, Suman Jana, and Ronghui Gu. [paper] [code]

[ICLR 2020] CLN2INV: Learning Loop Invariants with Continuous Logic Networks. Gabriel Ryan*, Justin Wong*, Jianan Yao*, Ronghui Gu, and Suman Jana. [paper] [code]

[Infovis 2018] At a Glance: Pixel Approximate Entropy as a Measure of Line Chart Complexity. Gabriel Ryan, Abigail Mosca, Remco Chang, and Eugene Wu. [paper] [code]

[Oakland S&P Workshops 2018] Simulated User Bots: Real Time Testing of Insider Threat Detection Systems. Preetam Dutta, Gabriel Ryan, Aleksander Zeiba, and Salvatore Stolfo. [paper]

[Oceans 2012] Oversampling MAVS for Reduction of Vortex-Shedding Velocity Sensing Noise. Albert J. Williams, Gabriel Ryan, and Fredrik Thwaites. [paper]


National Defense Science and Engineering Graduate Fellowship (NDSEG). Won NDSEG Fellowship for proposal “Proximal Gradient Analysis for Vulnerability Detection and Defense.” 2019 [proposal]

NSF Graduate Research Fellowship Honorable Mention. Received honorable mention for proposal “Modeling and Simulating Adversarial User Behavior with Sequential VAEs.” 2018