🚨CARBANAKv2 🚨EDR/XDR/Provenance dataset with dwell time, lateral movement, naturalistic background activity now available at https://t.co/FBUouGJrex !! Try the @PrismNdss26 interactive tutorial colab notebook to explore the attack!
New rule: if your insightful comment on AI was already in this super cool 1977 paper about "AI is becoming so powerful it will change the world as we know it," you lose. (1/10)
FYI threat detection/investigation community -- I was sleeping on this and know from @PrismNdss26 that some groups are redundantly developing this architecture r/n. Probably better to build on top of @Livermore_Lab's WinTap system: https://t.co/VArfdSBDZK
🇩🇪 JUST IN: Germany just unveiled real life “cyborg insects” built for the battlefield.
Developed by SWARM Biotactics, the system fuses live insects with neural interfaces, AI, and onboard sensors, turning them into stealth micro recon units.
Field tested within a year, these bio hybrids are quieter than drones, highly mobile, and capable of slipping into places machines can’t reach.
The future of surveillance just got smaller.
@adityagp Neat! While still in preprint, I suggest changing buzzy phrasing to something more culturally sensitive — experiential knowledge, institutional knowledge, etc.?
@MuhammadAdilIn1@PrismNdss26@akulgoyal00 TL;DR -- @PrismNdss26 is basically a gift-wrapped starter kit for conducting effective systems research on real-world security operations, an area that frankly needs more attention and talent. Join us!
At @NDSSSymposium for the Monday workshops? I *can’t tell you* how excited I am for the inaugural @PrismNdss26. I’ve asked my poor students to engage in a lot of (largely thankless) work developing community resources the past few years. We’re bringing it all to PRISM. 🧵
@MuhammadAdilIn1@PrismNdss26@akulgoyal00 This work joins a ton of other amazing talks about sophisticated threat analysis and how to conduct applied and rigorous research in the area. Tutorials on on push-button PIDS evaluations, threat intelligence extraction, and development of new attack engagements. 🧵
We demonstrate comparable alert triage rates to costly provenance analysis -- 84% global reduction in false alerts -- by examining an alert-triggering process' *instantaneous* context. By foregoing provenance, we are able to process thousands of alerts per sec.