The Cybersecurity Defenders Podcast

30:00

Securing AI agent identity and authority with...

The Cybersecurity Defenders Podcast ·

2026/10/01

Today we're speaking with Geoffrey Mattson, CEO of SecureAuth, about identity and authority for AI agents: what changes when software stops being something a human uses and starts taking actions on its own.Geoffrey is a serial entrepreneur working at the intersection of cybersecurity and AI. Before SecureAuth he was CEO of Xage Security and co-founded MistNet.ai (acquired by LogRhythm), after product and engineering leadership roles at Juniper Networks, Huawei, Nortel and Bell Labs across

en-us

36:41

Physical AI and self-learning machines with Dr....

The Cybersecurity Defenders Podcast ·

2026/09/16

Today we're speaking with Dr. Amarjot Singh, Founder & CEO of Skylark Labs, about physical AI — what changes when a model leaves the server and has to perceive, decide and act inside a machine that moves through the real world.Dr. Singh earned his PhD in artificial intelligence and deep learning from the University of Cambridge, and has worked as a research fellow at Stanford University and on DARPA research focused on artificial general intelligence. His work spans computer vision,

en-us

34:31

Intel Chat: Claude models reached real systems, an AI...

The Cybersecurity Defenders Podcast ·

2026/09/11

Intel Chat with Matt Bromiley and Chris Luft.• An Anthropic researcher quits over where the race is heading. Jacob Coxon, who trains models on large amounts of data, is leaving both Anthropic and the AI industry: he believes the leading labs are racing toward self-improving systems they may not be able to control, and that competition will push them there anyway. Matt's problem with the genre of exit: if the people who care most about safety walk out, walking out guarantees they have no

en-us

32:59

Intel Chat: OpenAI's Astra hits Critical, DEF CON...

The Cybersecurity Defenders Podcast ·

2026/09/03

Intel Chat with Matt Bromiley and Chris Luft.• OpenAI says Astra is the first of its models to reach the "Critical" cybersecurity capability level under its Preparedness Framework — the tier that means a model can independently find and exploit zero-days across well-defended systems, or run an end-to-end attack from a high-level instruction. Astra scored perfectly on ExploitBench, independently discovered two zero-days, escaped a browser sandbox, and chained flaws in a hardened OS to get

en-us

30:14

Intel Chat: Hugging Face AI-agent breach, WP2Shell,...

The Cybersecurity Defenders Podcast ·

2026/07/30

Intel Chat with Matt Bromiley and Chris Luft.Matt and Chris break down four stories from the week in threat intel:• Hugging Face's security incident disclosure: an intrusion conducted end-to-end by an autonomous AI agent system — a malicious dataset exploiting two code-execution paths, thousands of actions across short-lived sandboxes, self-migrating C2 — and why the forensics had to run on the open-weight GLM 5.2 model after hosted frontier models refused to analyze real attack artifacts.•

en-us

35:06

Building trustworthy AI with Rob van der Veer [341]

The Cybersecurity Defenders Podcast ·

2026/07/29

Today we're speaking with Rob van der Veer, Chief AI Officer at Software Improvement Group, about how organizations can build trustworthy AI in an era of rapidly evolving technology and regulation — AI security, threat modeling, international standards, and the new challenges posed by agentic AI.Rob is a global leader in AI security, software engineering, and international AI standards, with more than 30 years of experience in artificial intelligence. He has played a leading role in developing

en-us

35:27

AI Chat: The Hugging Face / OpenAI breach — the...

The Cybersecurity Defenders Podcast ·

2026/07/23

AI Chat with Maxime Lamothe-Brassard and Chris Luft — a special episode.One story, pulled apart start to finish. In mid-July 2026, Hugging Face disclosed a breach of its production infrastructure carried out end-to-end by an autonomous AI agent. Five days later, OpenAI revealed the attacker was its own models — GPT-5.6 Sol and a more capable unreleased model — which broke out of an internal cyber-capability evaluation called ExploitGym and reached into Hugging Face's production systems to steal the

en-us

23:18

AI Chat: Grok CLI data exfiltration, AI vs. patching,...

The Cybersecurity Defenders Podcast ·

2026/07/14

AI Chat with Maxime Lamothe-Brassard and Chris Luft.A new segment on the podcast: AI news in cybersecurity that is less than 24 hours old, discussed while it is still hot. Joining Chris for these conversations is LimaCharlie founder and CEO Maxime Lamothe-Brassard.In this episode:• Nipun Gupta (founder of Optimus Labs) reports that xAI's Grok Build CLI packaged and uploaded an entire local Git repository — commit history, branches and .env files with API keys — to a Google Cloud bucket; wire-level

en-us

34:26

Intel Chat: Dialogflow Rogue Agent, ghost phishing,...

The Cybersecurity Defenders Podcast ·

2026/07/09

Intel Chat with Matt Bromiley and Chris Luft.Matt and Chris break down four stories from the week in threat intel:• Varonis Threat Labs' "Rogue Agent" — a permission boundary flaw in Google Dialogflow CX's Code Blocks feature that could let an attacker with a single permission (dialogflow.playbooks.update) inject persistent malicious code into a chatbot's execution pipeline and silently exfiltrate conversations; Google has fully patched it, no customer action required.• The EvilTokens campaign and

en-us

33:07

Ransomware in the age of agentic AI with Behnaz...

The Cybersecurity Defenders Podcast ·

2026/07/08

Today we're speaking with Behnaz Karimi, an independent researcher specializing in ransomware and agentic AI systems, Senior Cybersecurity Analyst at Accenture, and founder of Tremorina, about how ransomware is evolving to target AI systems, machine learning pipelines, and autonomous agents.With more than 20 years of experience in cybersecurity, Behnaz is also a leader within the OWASP AI Exchange, where she helps develop AI security frameworks and contributes to international AI security standards

en-us

33:53

Intel Chat: Hijacked AI backends, billboard hacks,...

The Cybersecurity Defenders Podcast ·

2026/07/03

Intel Chat with Matt Bromiley and Chris Luft.Matt and Chris break down four stories from the week in threat intel:• Zenity researchers observed three campaigns where attackers hijacked internet-exposed AI inference endpoints (Ollama, LiteLLM) as free model backends for offensive operations — including the Strix and HexStrike-AI pentesting frameworks and a Codex agent posing as a "security auditor" — enabled by no-auth defaults and placeholder API

en-us

30:01

Intel Chat: Cisco CUCM exploited, ransomware...

The Cybersecurity Defenders Podcast ·

2026/07/01

Intel Chat with Matt Bromiley and Chris Luft.Matt and Chris break down four stories from the week in threat intel:• Cisco CUCM (CVE-2026-20230) — a web-dialer SSRF that chains to root-level RCE, exploited in the wild less than 24 hours after the PoC and full exploit chain were published.• The latest Ransomware Tool Matrix (RTM) / Ransomware Vulnerability Matrix (RVM) update, profiling three active groups — The Gentlemen, DragonForce and Warlock — and the BYOVD and legit-admin-tool tradecraft they

en-us

42:38

The evolving fraud landscape in the age of AI with...

The Cybersecurity Defenders Podcast ·

2026/06/30

Today we're speaking with Tamas Kadar, CEO / Co-Founder of SEON, about building a safer digital world for businesses. We touch on fraud, how it's evolved in the age of AI, and what we can do to protect ourselves against it.Tamas' entrepreneurial path began at Corvinus University in Budapest, where the vision for SEON first took shape. Co-founding a cryptocurrency exchange opened his eyes to the scale and complexity of online fraud, sparking the idea for something better. In 2017, that “something

en-us

34:44

Anthropic restriction, ServiceNow incident, Fortinet...

The Cybersecurity Defenders Podcast ·

2026/06/28

In this episode of The Cybersecurity Defenders Podcast, we discuss some intel being shared in the LimaCharlie community.Reports state that the US government issued an export control order restricting access to anthropic newly released cloud mythos five and fable five models for foreign nationals.ServiceNow disclosed a security incident involving an unauthenticated access for an API endpoint that allowed users to query data from customer instances without proper authentication.A large scale

en-us

37:05

Last call for Defenders - How we're actually using AI...

The Cybersecurity Defenders Podcast ·

2026/06/20

Join us for the final episode of Defender Fridays as Eric Capuano, creator of Defender Fridays and co-founder of Digital Defense Institute, closes out the series with a candid conversation on how he's actually building and running agentic workflows in the SOC today.At Defender Fridays, we delve into the dynamic world of information security, exploring its defensive side with seasoned professionals from across the industry. Our aim is simple yet ambitious: to foster a collaborative space where ideas

en-us

28:31

FFmpeg's 21 zero-days, Ruby cooldown feature,...

The Cybersecurity Defenders Podcast ·

2026/06/15

In this episode of The Cybersecurity Defenders Podcast, we discuss some intel being shared in the LimaCharlie community.DepthFirst reported that it's autonomous security agent discovered 21 previously unknown vulnerabilities in FFmpeg, a widely deployed multimedia framework used across browsers, streaming infrastructure, and other systems that process media. Bundler, 4.0.13 introduces a new security feature called cooldown, aimed at reducing the impact of software supply chain attacks in the Ruby

en-us

32:04

AI-assisted SOC training with Carlo Anez / Defender...

The Cybersecurity Defenders Podcast ·

2026/06/12

Join us for this week's Defender Fridays as Carlo Anez, Founder and Lead Instructor at IgniteCyber Academy and DEFCON Training Instructor, breaks down how to build practical blue team skills using open-source labs, MITRE ATTACK, and real-world defender workflows, and where AI fits into the picture without replacing the analyst.At Defender Fridays, we delve into the dynamic world of information security, exploring its defensive side with seasoned professionals from across the industry. Our aim is

en-us

30:31

Building practical blue team skills using AI-assisted...

The Cybersecurity Defenders Podcast ·

2026/06/05

Join us for this week's Defender Fridays as Bobby Ford, Chief Strategy and Experience Officer at Doppel, talks about open-source labs, MITRE ATT&CK, and real-world defender workflows.At Defender Fridays, we delve into the dynamic world of information security, exploring its defensive side with seasoned professionals from across the industry. Our aim is simple yet ambitious: to foster a collaborative space where ideas flow freely, experiences are shared, and knowledge expands.About Our GuestBobby

en-us

29:05

"Megalodon" Malware in GitHub, Malware-Slop steals...

The Cybersecurity Defenders Podcast ·

2026/06/01

Originally recorded: Friday May 29, 2026In this episode of The Cybersecurity Defenders Podcast, we discuss some intel being shared in the LimaCharlie community.A large-scale software supply chain attack dubbed “Megalodon” infected thousands of GitHub repositories with credential-stealing malware in a highly automated campaign that unfolded over a six-hour period on May 18, 2026.Researchers from OX Security have identified a malicious npm package named “mouse5212-super-formatter” that was designed to

en-us

30:19

From PentestGPT to production: The state of...

The Cybersecurity Defenders Podcast ·

2026/05/30

Join us for this week's Defender Fridays as Charles Grandjean, CTO and Co-founder at Hexiagon AI, breaks down where AI-assisted pen testing actually stands today and what it means for both red teams and defenders.At Defender Fridays, we delve into the dynamic world of information security, exploring its defensive side with seasoned professionals from across the industry. Our aim is simple yet ambitious: to foster a collaborative space where ideas flow freely, experiences are shared, and knowledge

en-us

All Episodes

Similar Podcasts

Lead With AI

Tamara Nall

The Automated Daily

TrendTeller

My Weird Prompts

Daniel Rosehill

LessWrong (Curated & Popular)

LessWrong

脈報

思思主播