2026 - Nothing Looks Broken: Investigating AI When the Model Behaves
2026 - Nothing Looks Broken: Investigating AI When the Model Behaves.
Summary
Overview: Um so thank you everybody for being here today. My talk is nothing looks broken investigating AI when the model behaves. Um my name is Kiara Delo. Um I'm an industry professional in the digital forensics and incident response um sector. Um I've been doing that for a little under two years, but I've always worked in tech. Um currently doing my masters in cyber ops. That's kind of how I like was interested in this talk. Uh cyber ops is like more like red offensive um learning. Um I thought it woul
Key Topics: d make me a better blue teamer. actually made me a lot crazier cuz like I thought like breaking things it just made like now I break things and I'm
Related talks
AUSCERT·25 min
Scaling Capability or Scaling Risk? A Look at AI at the Coalface.
RSAC Cybersecurity·3 min
Industry experts analyze emerging threats surrounding Quick Look: The Supply Chain is Broken: The Case of BLUEMONDAY & How To Own Everything.
BSidesCharm·21 min
Coverage of 2026 - Using AI in Threat Modeling from the conference program.