Jekyll2026-08-26T18:36:21+00:00https://secure-reasoning-lab.github.io/feed.xmlSecure Reasoning LabResearch lab at NYU Abu Dhabi working on large language models, cyber reasoning systems, and AI security.Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/NYU Tandon launches NSOC2026-08-24T00:00:00+00:002026-08-24T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2026/08/nsoc-launchNYU Tandon has launched the NYU Software Supply Chain Security Operations Center (NSOC), an NYU Center for Cybersecurity initiative that embeds master’s students in open-source communities for a year of hands-on supply-chain security work. Prof. Jiahao Yu co-founded NSOC with Justin Cappos, Andrew Nesbitt, and Vlad-Stefan Harbuz. The first cohort starts in January 2027. More at nsoc.engineering.nyu.edu.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/Jiahao Yu joins NYU Abu Dhabi2026-06-04T00:00:00+00:002026-06-04T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2026/06/joining-nyuadJiahao Yu will join the Department of Computer Engineering at New York University Abu Dhabi as a Tenure-Track Assistant Professor. The Secure Reasoning Lab is actively looking for self-motivated Ph.D. students and postdocs. See Join Us.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/PatchAgent selected as a CSAW 2025 finalist2025-10-06T00:00:00+00:002025-10-06T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2025/10/patchagent-csawOur work PatchAgent was accepted as a CSAW 2025 finalist (Technical Impact Runner-up). We presented the work in New York City.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/EntroPO ranks 1st on SWE-bench Lite (open-weight)2025-10-05T00:00:00+00:002025-10-05T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2025/10/entropo-leaderboardThe official SWE-bench Verified and SWE-bench Lite open-weight leaderboards were updated. EntroPO ranks 1st on SWE-bench Lite and 5th on SWE-bench Verified, behind only models about 10× larger.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/GPO covered by MIT Technology Review China2025-10-05T00:00:00+00:002025-10-05T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2025/10/gpo-mittrOur work GPO: Learning from Critical Steps to Improve LLM Reasoning was covered by MIT Technology Review China.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/Soft-label toxicity work covered by MIT Technology Review China2025-03-18T00:00:00+00:002025-03-18T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2025/03/soft-label-mittrOur work Soft-Label Integration for Robust Toxicity Classification was covered by MIT Technology Review China.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/GPTFuzzer wins the Geekcon 2023 Breakthrough Award2024-04-18T00:00:00+00:002024-04-18T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2024/04/gptfuzzer-geekconOur GPTFuzzer work received the Geekcon 2023 Annual Themed Debate Breakthrough Award and was covered by SECGEEK.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/BandFuzz wins first prize at SBFT 20242024-04-16T00:00:00+00:002024-04-16T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2024/04/bandfuzz-sbftBandFuzz won first prize in the SBFT fuzzing competition and was covered by McCormick School of Engineering News.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/Custom GPT prompt-injection work covered by WIRED2023-11-29T00:00:00+00:002023-11-29T00:00:00+00:00https://secure-reasoning-lab.github.io/posts/2023/11/wired-prompt-injectionOur prompt-injection study on custom GPTs was covered by WIRED.]]>Secure Reasoning Labjy5951@nyu.eduhttps://hubertyoo.github.io/