Excited to finally share our #NeurIPS2025 paper "🔮PurpCode: Reasoning for Safer Code Generation"! 🙌
👐 First post-training recipe for training safe code reasoning models
🚀 SOTA for cybersafety + utility, outperforming Sonnet 4, o4-mini, R1
🥇 Winner of 2025 Amazon Nova AI Challenge
📝 Paper: https://t.co/9aOoiL5zgJ
🧵👇 1/11
🚀 Made Possible by Incredible People!
This wouldn't have been possible without my brilliant fellow core contributors @JiaweiLiu_ and @zhewang_20! 🙌
Massive thanks to the entire PurpCode Team and our incredible advisors @ffmagicbean, @Ismini_L, and @LingmingZhang for their unwavering support!
Special shoutout to the Amazon Nova AI Challenge Team for making this opportunity possible!
11/11
🔥So excited to present our paper at @SOUPSConference
📊Check out the paper here:
Can You Walk Me Through It? Explainable SMS Phishing Detection using LLM-based Agents
https://t.co/cUuR456Zny
Thanks a lot for @ffmagicbean helping me in this paper!!
Meet the champions of the Amazon Nova AI Challenge, where university teams around the world went head-to-head to break and defend LLMs under real adversarial pressure:
🏆 Defending: UIUC (PurpCorn-PLAN)
🏆 Attacking: Purdue (PurCL)
🥈 CTU Prague & Nova Lisbon
These students just raised the bar for secure Gen AI.
Full recap: https://t.co/EaP0maph1c
[ACM CCS 2025] Want to host a workshop at CCS 2025? Check out the "Call for Workshops" here. 😃 Deadline March 14 (AoE) @acm_ccs
https://t.co/tkisr4HUVE
@IEEESSP IEEE SP 2025 opened the "Call for Workshops" much earlier this year, to give workshop organizers more time to set up the workshop and review papers (proposals deadline: September 26, 2024). Please consider submitting🔥🔥🔥: https://t.co/w7P6FnCMDw
Upcoming at @USENIXSecurity’24 — In (academic) systems security research, name checking @MITREattack has been the “peer review armor” of choice for a lot of work recently. But do these papers understand what ATT&CK is(n’t)? What about commercial products?
I'm so excited to say I'll be joining @ASU's School of Computing and Augmented Intelligence as an Asst. Professor this fall!
So many thanks to @ffmagicbean, @eredmil1, @yoshi_kohno, @yazz_acar, @adamaviv, and the many other mentors & friends who supported me through this journey
Woohoo, another #CHI2024 paper conditionally accepted to round out the PhD!
Excited to discuss how mental models used in deepfake moderation result in identity-based biases and harm to real users. Details to follow!
🎓🎉Defended my Ph.D. dissertation today!
🙏🏻Big thanks to my advisor @ffmagicbean and my committee Dr. Carl Gunter, Dr. Ravishankar Iyer, Dr. Zbigniew Kalbarczyk, and @lcavallaro!
Thank you all to my friends, collaborators, and family.
I will join @tiktok_us next month 😎
I just learned that I got Tenure! --- It is such a privilege to work with our amazing students, collaborators, and colleagues. Very grateful to my family, friends, mentors, and the supportive department and university!