Windows Kernel Programming, Second Edition by Pavel Yosifovich is on sale on Leanpub! Its suggested price is $37.95; get it for $24.21 with this coupon: https://t.co/eUlCRcb3es @ZODIACON
These CVEs grew out of a breakthrough in how I use local language models: making them more capable without making them bigger.
The research that made this possible is now public, with the paper, code and experimental results:
https://t.co/mJB69NTMuC
Just to put things right:
1/ Many read my #ARTEX signature release as "an IOC list". It isn't. The #IOCs expire within a year by design. The real release is the workflow: how to turn the next ARTEX-style attack into detections as fast as the attacker moves.
2/ ARTEX is an #LLM harness. Swap the model, prompts or infra and every IOC changes. What changes much less is how an agent behaves: machine-speed recon chains, ~1/s #PasswordSprays with rotating UAs, self-correcting API retries, systematic record enumeration.
3/ So the pack is behavior-first. Those patterns live in Sigma correlations, Sentinel KQL and Zeek SumStats on the upper network layers, not in packet filters. IPs are clearly labelled T3/T4 context for retro-hunting what already happened.
4/ The #playbook is the core: verify the source, classify how specific an indicator really is, assign a tier, route it to the right format, expire it. We applied it to four campaigns with an LLM assisting and humans gating every verification step. Next trail, same loop.
5/ That's the big picture: attackers use LLMs to compress weeks into hours. Defenders can use LLMs to compress "new report → tested detection" into hours too, as long as humans keep the verification gates. We must defend atacker's powered LLM/#AI with AI.
6/ The Zeek section shows how to carry the same behavioral logic into network sensors you already run. Playbook, rules and tests: [link]. Break them, send FP/TP reports. That's how this grows.
@HexasBosas I do not live in China.
However, I was deeply impressed by your efforts to create an environment where students can thrive.
I am quietly rooting for you.
Slides from the talk @mlippautz and I gave at the recent @offensive_con in Tokyo: https://t.co/6251OZx80V
Blog post for the Fuzzing vs. AI part: https://t.co/OGF11RLqXz