Listen to Talos security experts as they bring their hot takes on current security topics and Talos research to the table. Along the way Mitch, Liz, Matt and a rotating chair of special guests will talk about anything (and we mean anything) that's on their minds, from the latest YouTube trends to Olympic curling etiquette. New episodes every other Thursday.
Welcome back to the podcast where the structure is theoretical and the only certainty is uncertainty. In this episode, the crew reassembles after a totally intentional and not-at-all accidental hiatus (blame is assigned, forgiveness is not).
We cover:
We also mourn Bill's departure as he abruptly quits the podcast after one pun too many.
As always, we make absolutely no guarantees that this episode makes any sense whatsoever.
Every week, our host brings on a new guest from Talos or the broader Cisco Security world to break down a complicated security topic in just five or 10 minutes. We cover everything from breaking news to attacker trends and emerging threats.
Hazel welcomes back Ryan Fetterman from the SURGe team to explore his new research on how large language models (LLMs) can assist those who work in security operations centers to identify malicious PowerShell scripts. From teaching LLMs through examples, to using retrieval-augmented generation and fine-tuning specialized models, Ryan walks us through three distinct approaches, with surprising performance gains. For the full research, head to https://www.splunk.com/en_us/blog/security/guiding-llms-with-security-context.html