ToxSec - AI and Cybersecurity Podcast

Est. audience

100

Apple rating

5 from 1

Cadence

Every two weeks

Latest

2026-08-18

By

ToxSec

Based on

12 recent episodes

• Covers: Security vulnerabilities in AI models, autonomous agents, supply chain risks, jailbreaks, and offensive AI threats.
• For: Cybersecurity professionals, AI engineers, and technical security leaders.
• Best for: Security engineers and developers deploying or defending enterprise AI systems.
• Skip if: Non-technical listeners looking for general AI productivity tips.

Start with

• Hacking Hugging Face to Cheat a Benchmark: Explains how AI agents attacked a sandbox proxy to access production databases.
• Mozilla Mythos Harness: AI Bug Hunting Without The Slop: Shows how to wrap AI models in harnesses to find software vulnerabilities effectively.
• You Downloaded Gemma 4 from Hugging Face. Is It Safe to Run?: Covers supply chain risks, serialization exploits, and verification for local model weights.

Visit

Summarised by AI from 12 recent episodes. Audience estimate and Apple rating from Podscan, checked 2026-11-03; treat the estimate as a guide and ask the show for its own numbers. Prices are not included. Report a mistake.