←
itszn1,368 posts
itszn avatar✓

itszn ✓

@itszn13

Amy | Security researcher @ OpenAI | stackchk.fail/ctf.txt | bsky: nyanbox.stackchk.fail | LLM ART: bsky.app/profile/alternet.si…

◷ Joined June 2011▧ 174 Photos and videos
itszn avatar
itszn@itszn13·Nov 5

GPT-6 Cyber is our latest model for vulnerability research and redteaming Combining Astra’s innate capabilities with training designed and inspired by the work of our vulnerability research team including @ky1ebot @daveaitel @halvarflake @clintgibler and many others!

itszn avatar
itszn@itszn13·18h

We found that GPT-6.2 was another step up in vulnerability research akin to the leap we saw from 5.6 -> 6 On unseen v8 bugs: an increase of 22%! Along with this, our team worked hard to bring large improvements in secure code generation and secure and complete patch generation

Post attachmentPost attachmentPost attachmentPost attachment
Xiangyu Qi avatar
⟳ itszn retweeted
Xiangyu Qi@xiangyuqi_pton·Nov 5

Introducing GPT-6 Cyber! We trained it for advanced cybersecurity work with improved alignment. It has been powering our security work for quite a while and has been behind many of our recent security highlights: finding and helping patch high-severity vulnerabilities in Firefox, developing exploits and proposing patches for Linux kernel vulnerabilities, and strengthening OpenAI’s own infrastructure through red-teaming. Today, we’re rolling it out to Daybreak Red to keep the cyber frontier in defenders’ hands. openai.com/index/introducing…

itszn avatar
itszn@itszn13·Nov 4

Great work by @ky1ebot The most interesting part of this was seeing the model discover new previously unknown exploitation techniques Since we ask it to exploit every single bug it is stuck with some very constrained limited bugs which require very creative thinking to pull off

Post attachment
Eric Wallace avatar
⟳ itszn retweeted
Eric Wallace@Eric_Wallace_·Nov 4

We are now allocating a significant amount of our frontier compute towards discovering and patching vulnerabilities in open source codebases, fully pro bono. In one case, we studied the Linux kernel, which is a particularly load-bearing piece of software at OpenAI. Before AI, security researchers might discover ~20 local privilege escalation (LPE) vulnerabilities in Linux in a typical year. In one week's time, our upcoming frontier cyber model was able to find ~1000 LPE vulnerabilities using about $1M of tokens. In the process, it was able to discover at least 10 novel classes of Linux exploitation techniques.

Post attachment
itszn avatar
itszn@itszn13·Nov 3

Firefox 159.0 just fixed 41 sechigh vulnerabilities found by me and @ky1ebot Most of these leads to code exec in the renderer! Along side a heroic effort from the Mozilla security team to secure Firefox with agents! One of many projects we are working to harden, more to come

Post attachment
kylebot avatar
⟳ itszn retweeted
kylebot@ky1ebot·Oct 23

Sandboxing is really hard especially when facing our cyber capable models. So, we used our cyber capable model to red-team our own sandbox stack and found issues in many layers of the stack, including but not limited to Kata, gVisor, docker, and Linux.

itszn avatar
itszn@itszn13·Oct 23

The critical Brotli RCE vulnerability discovery came out of our large scale infrastructure code scanning efforts Great research by @k_tr4n and @_sy1vi3 in assessing the widespread impact of this bug Update your Node.js, Bun, Envoy, anything using Brotli ASAP!

Post attachmentPost attachment
LCFR avatar
⟳ itszn retweeted
LCFR@lcfr_hax·Oct 22

Team work makes the dream work <3 We wanted to do something a bit different than using LLM's to generate all the pieces from exploit, writeup and art. We decided on a human created comic to offset the LLM usage in our release, that tells the tale with some exaggerated scenarios inspired from a few movies. If you liked the art (or want your own exploit story/comic..) check out her work at ibiscraft.art

Post attachmentPost attachmentPost attachmentPost attachment
itszn avatar
⟳ itszn retweeted
itszn@itszn13·Oct 21

Largest credit goes to @lcfr_hax for the earliest recent discovery of the bug class. This underlying engine issue was so wide it invited a lot of parallel discovery. As we coordinated our findings the scope of the problem continued to expand!

Calif avatar
⟳ itszn retweeted
Calif@calif_io·Oct 21

Let’s set the record straight: @lcfr_hax was the first to discover php2shell and develop a working exploit. See his August 5 tweet: x.com/lcfr_hax/status/208503… His work convinced the PHP Foundation to invest in fixing this entire bug class. He then worked around the clock to review, test, and retest the patches.

itszn avatar
itszn@itszn13·Oct 21

php2shell is the most consequential vulnerability I have ever helped discover. I am proud of how our team worked closely in coordination with the PHP Foundation to provide support and to harden the patch in preparation for this release.

Please read more about our approach:

Post attachmentPost attachment
itszn avatar
itszn@itszn13·Sep 1

When testing Astra on ExploitBench we found that it was able to achieve 100% ACE on all 41 CVEs So we made a contamination free internal port using only V8 CVEs from the past 3 months. Astra still showed a major capability increase over 5.6 and did so with a lot fewer tokens!

Post attachment