Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Enterprise Security Weekly (Audio)

Enterprise Security Weekly (Audio) artwork

AI Red Teaming and AI Safety - Sounil Yu, Amanda Minnich - ESW #371

Aug 9, 20242 hr 18 minAudio
ShareXLinkedInFacebookWhatsAppEmail

In this interview we explore the new and sometimes strange world of redteaming AI. I have SO many questions, like what is AI safety? We'll discuss her presence at Black Hat, where she delivered two days of training and participated on an AI safety panel. We'll also discuss the process of pentesting an AI. Will pentesters just have giant cheatsheets or text files full of adversarial prompts? How can we automate this? Will an AI generate adversarial prompts you can use against another AI? And finally, what do we do with the results? Resources: PyRIT AI redteaming tool Microsoft's AI redteaming guide We chat with Sounil Yu, co-founder of LLM access control startup, Knostic. We discuss both the experience of participating in Black Hat's startup competition, and what his company, Knostic, is all about. Knostic was one of four finalists for Black Hat's Startup Spotlight competition and was announced as the winner on August 6th. References DarkReading: Knostic Wins 2024 Black Hat Startup Spotlight Competition Knostic's Website, in the enterprise security news, AI is still getting a ton of funding! Netwrix acquires PingCastle Tenable looks for a buyer SentinelOne hires Alex Stamos as their new CISO Crowdstrike doesn't appreciate satire when it's at their expense Intel begins one of the biggest layoffs we've ever seen in tech Windows Downdate RAG poisoning GPT yourself The Xerox Hypothesis All that and more, on this episode of Enterprise Security Weekly. Visit https://www.securityweekly.com/esw for all the latest episodes! Show Notes: https://securityweekly.com/esw-371

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. AI is not killing bug bounty, can an AI ever have an "Identity", and the news - Michiel Prins, Douglas Day - ESW #485

    Nov 16, 20261 hr 32 minAudio

    Interview with Douglas Day and Michiel Prins AI Is Not Killing Bug Bounty: It Is Raising the Bar AI is making it easier for more people to attempt vulnerability research, but Douglas' experience shows that the biggest...

    Credit the people on this episode

  2. Assessing risk at the speed of change, coordinated disclosure, and the news - Danielle Russell - ESW #484

    Nov 9, 20261 hr 43 minAudio

    Interview - Danielle Russell - The Attack Surface Changed: Who Reassesses Risk After the Approval? The attack surface now changes faster than any team can reassess it, as employees add integrations, grants, and agents...

    Credit the people on this episode

  3. Shifting Cyber Turtles with Casey Ellis, the Vibe Check, and the News - Casey Ellis - ESW #483

    Nov 2, 20261 hr 42 minAudio

    Interview with Casey Ellis Our focus for this interview with Casey Ellis are the massive changes in: Vulnerability Discovery Vulnerability Disclosure Exploitation and Remediation The goal is to understand how...

    Credit the people on this episode

  4. Building a parallel Internet, security buzzwords that should be retired, and the news - Barrett Lyon - ESW #482

    Oct 26, 20261 hr 26 minAudio

    Interview with Barrett Lyon Why do we need a Parallel Internet? Barrett details his journey to build truly private access to the Internet. My first thought was, "why not VPN? Why not TOR?" He has good answers to both....

    Credit the people on this episode

  5. Securing AI on the Endpoint, Anthropic Dreams of AI Replicants, and the News - Michael Jenkins - ESW #481

    Oct 19, 20261 hr 33 minAudio

    Interview with Michael Jenkins from ThreatLocker Securing AI on the Endpoint - Zero Trust or Bust Michael joins us for the first time to discuss strategies for securing the latest evolution of AI: local endpoint-based...

    Credit the people on this episode