@perribus Profile picture

Perri Adams

@perribus

Special Assistant to the Director @DARPA • AIxCC • Adj Professor @SAISHopkins • Prev running @DEFCON Capture the Flag (CTF) • @RPISEC Alumna • Opinions mine

Similar User
offensivecon photo

@offensive_con

REcon photo

@reconmtl

Matteo Rizzo photo

@_MatteoRizzo

RET2 Systems photo

@ret2systems

Pietro Borrello photo

@borrello_pietro

Saar Amar photo

@AmarSaar

Brandon Falk photo

@gamozolabs

itszn photo

@itszn13

Vector 35 photo

@vector35

Samuel Groß photo

@5aelo

James Forshaw photo

@tiraniddo

Rolf Rolles photo

@RolfRolles

acez photo

@amatcama

Zardus@DEFCON.social photo

@Zardus

Adam Doupé photo

@adamdoupe

Pinned

Some thoughts on the first year of AIxCC linkedin.com/posts/activity…

Tweet Image 1

Perri Adams Reposted

I'm sick tired of people pushing their "memory-safe language" agenda when a viable solution is within reach.

Tweet Image 1

Perri Adams Reposted

1/10 Today we're launching FrontierMath, a benchmark for evaluating advanced mathematical reasoning in AI. We collaborated with 60+ leading mathematicians to create hundreds of original, exceptionally challenging math problems, of which current AI systems solve less than 2%.

Tweet Image 1

Perri Adams Reposted

🤖 Our AIxCC cyber reasoning system, Atlantis🌊, will take on the TKCTF challenge alongside student hackers! Let’s see if LLMs can spot and patch bugs in a real-time CTF environment!

🚩 Ready for a challenge? Join us for TKCTF on Nov 22! Open to the public and $1,000 prize for 1st place. Register your team here: ctf.gts3.org 🔗 #CTF #Cybersecurity #TKCTF

Tweet Image 1


Perri Adams Reposted

“We also feel that this variant-analysis task is a better fit for current LLMs than the more general open-ended vulnerability research problem. ” therecord.media/google-llm-sql…


Perri Adams Reposted

Hello hackers! In case you missed it at @DEFCON: @perribus, @adamdoupe, @the_robwaz, @TheConnorNelson, @TheDarkTangent and I announced @DEFCONAcademy! I kept meaning to spread the word, and now that there's hype (news.asu.edu/20241031-scien…), it's time for the thread! Read on! 🧵


“Earlier this year at the DARPA AIxCC event, Team Atlanta discovered a null-pointer dereference in SQLite, which inspired us to use it for our testing to see if we could find a more serious vulnerability.”

Today @Google Project Zero and @GoogleDeepMind shared how they’ve used an LLM to catch vulnerabilities in real world code with their project “Big Sleep.” This is a huge step for using AI to assist today’s cyber defenders. googleprojectzero.blogspot.com/2024/10/from-n…



Honored to receive a Most Inspiring Up and Comer award in this year’s CyberScoop 50, alongside some fantastic colleagues and friends (Nick Polk, @selenalarson @bailey_bickley @adamski_morgan etc., etc.) Thank you to @CyberScoopNews and @gregotto for such a lovely event today

Tweet Image 1
Tweet Image 2
Tweet Image 3

Perri Adams Reposted

🌟 Congratulations to the winners of the 2024 #CyberScoop50 Most Inspiring Up-and-Comer Award! This award honors the next generation of cybersecurity leaders—trailblazers who are already making a significant impact early in their careers. With forward-thinking approaches, these…


Had a lovely time teaching this class — and yet again, pwn.college was such a fantastic resource

I just wrapped up an incredibly insightful workshop, "The Science of Hacking," led by @Perribus and hosted by @alperovitch at @SAISHopkins The session provided insights by connecting the command line to national policy. Thank you again for a fantastic session!

Tweet Image 1


Perri Adams Reposted

I just wrapped up an incredibly insightful workshop, "The Science of Hacking," led by @Perribus and hosted by @alperovitch at @SAISHopkins The session provided insights by connecting the command line to national policy. Thank you again for a fantastic session!

Tweet Image 1

Never to young to start them on category theory

Tweet Image 1
Tweet Image 2

Perri Adams Reposted

If you missed it this summer, The Science of Hacking: Weird Machines, Vulnerabilities, & Exploits, w/ @perribus is back! Oct 25, 26, 27, & 28 | 10 – 4:30PM @SAISHopkins students, apply by Oct 15 👇 Non-Hopkins participants, 📧👉Prof. @EllyRostoum alperovitch.sais.jhu.edu/round-2-the-sc…

Tweet Image 1

Perri Adams Reposted

Very excited to welcome @perribus back to the @Alperovitch this fall to teach her outstanding course on hacking, weird machines, & exploits. I had an absolute blast developing this important course as part of our Advanced Alperovitch Workshop Series! Join us @JHUBloombergCtr!

If you missed it this summer, The Science of Hacking: Weird Machines, Vulnerabilities, & Exploits, w/ @perribus is back! Oct 25, 26, 27, & 28 | 10 – 4:30PM @SAISHopkins students, apply by Oct 15 👇 Non-Hopkins participants, 📧👉Prof. @EllyRostoum alperovitch.sais.jhu.edu/round-2-the-sc…

Tweet Image 1


Perri Adams Reposted

How Benjamin Franklin is inspiring defenders to protect critical infrastructure scoopmedia.co/4cSvT65

Tweet Image 1

Perri Adams Reposted

Stay tuned for more! Until then, 💻👀👉 tinyurl.com/22dv97zx

Tweet Image 1

Perri Adams Reposted

Reminiscing from earlier this summer when @perribus taught an intensive course on hacking and weird machines (we even wrote exploits! 😎🤫). 📸from Day 3 - when Perri was still teaching over celebratory dinner with our students (w/@juanandres_gs, @EllyRostoum & @LeeFosterIntel)!

Tweet Image 1
Tweet Image 2

Perri Adams Reposted

Incredibly excited that @DARPA, under PM Mike Lack, has open sourced the technology from the RACE program on censorship-resilience communications that I helped start when I was there linkedin.com/posts/darpa_fr…


Perri Adams Reposted

🧙 This is a story about #ML models achieving high scores on task-specific benchmarks when (as we found) they are *guaranteed* to not actually solve that task, at all. This is no problem of noise. The problem statement itself is ill-defined. Here, Benchmark ≠ True Capability.

Tweet Image 1

The way we are currently evaluating LLMs for vulnerability detection might be flawed! New paper w/ @mboehme_ . Paper: arxiv.org/abs/2408.12986 Code: github.com/niklasrisse/To… (1/10)

Tweet Image 1


“There are two things that are dead sure, I don’t even have to call them predictions. One is the amount to data and amount of information will continue to increase…the other is that the demand for instance access to that information will increase. And those two are in conflict.”

“We’ve got to know something about the value of the information being processed.” It’s rare that a talk holds up after four decades, rarer still a talk about computers. Grace Hopper is at once so witty and so prescient. What a treasure from @NSAGov youtu.be/si9iqF5uTFk?fe…



“We’ve got to know something about the value of the information being processed.” It’s rare that a talk holds up after four decades, rarer still a talk about computers. Grace Hopper is at once so witty and so prescient. What a treasure from @NSAGov youtu.be/si9iqF5uTFk?fe…


Loading...

Something went wrong.


Something went wrong.