A Conversation with Bar-El Tayouri from Mend.io
Unsupervised Learning6 Touko

A Conversation with Bar-El Tayouri from Mend.io

➡ Get full visibility, risk insights, red teaming, and governance for your AI models, AI agents, RAGs, and more—so you can securely deploy AI powered applications with ul.live/mend

In this episode, I speak with Bar-El Tayouri, Head of AI Security at Mend.io, about the rapidly evolving landscape of application and AI security—especially as multi-agent systems and fuzzy interfaces redefine the attack surface.

We talk about:

• Modern AppSec Meets AI Agents
 How traditional AppSec falls short when it comes to AI-era components like agents, MCP servers, system prompts, and model artifacts—and why security now depends on mapping, monitoring, and understanding this entire stack.

• Threat Discovery, Simulation, and Mitigation
 How Mend’s AI security suite identifies unknown AI usage across an org, simulates dynamic attacks (like prompt injection via PDFs), and provides developers with precise, in-code guidance to reduce risk without slowing innovation.

• Why We’re Rethinking Identity, Risk, and Governance
Why securing AI systems isn’t just about new threats—it’s about re-implementing old lessons: identity access, separation of duties, and system modeling. And why every CISO needs to integrate security into the dev workflow instead of relying on blunt-force blocking.

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler

Chapters:

00:00 - From Game Hacking to AI Security: Barel’s Tech Journey
03:51 - Why Application Security Is Still the Most Exciting Challenge
04:39 - The Real AppSec Bottleneck: Prioritization, Not Detection
06:25 - Explosive Growth of AI Components Inside Applications
12:48 - Why MCP Servers Are a Massive Blind Spot in AI Security
15:02 - Guardrails Aren’t Keeping Up With Agent Power
16:15 - Why AI Security Is Maturing Faster Than Previous Tech Waves
20:59 - Traditional AppSec Tools Can’t Handle AI Risk Detection
26:01 - How Mend Maps, Discovers, and Simulates AI Threats
34:02 - What Ideal Customers Ask For When Securing AI
38:01 - Beyond Guardrails: Mend’s Guide Rails for In-Code Mitigation
41:49 - Multi-Agent Systems Are the Next Security Nightmare
45:47 - Final Advice for CISOs: Enable, Don’t Disable Developers

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

Jaksot(532)

Unsupervised Learning: No. 93

Unsupervised Learning: No. 93

Equifax fallout, BlueBorne, Microsoft RCE, iPhone X, Dumping AWS, Cassini, tech news, human news, ideas, discovery, recommendations, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

18 Syys 201742min

Unsupervised Learning: No. 92

Unsupervised Learning: No. 92

Equifax, Hutchins got Krebs'd, Russia used Facebook, Energy hacking, Anti-protester AI, High-pitched Assistant hacking, tech news, human news, ideas, discovery, recommendations, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

11 Syys 201729min

Unsupervised Learning: No. 91

Unsupervised Learning: No. 91

465K pacemaker patches, instagram leak, DJI bounty, Marketing departments messing up security news, false dichotomy in complex issues, IRS social media mining, death of the Sun, more fake Wells Fargo accounts, human echolocation, facial gestures as interface, discovery, recommendations, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

4 Syys 201737min

Unsupervised Learning: No. 90

Unsupervised Learning: No. 90

Swedish gov leak, OPM hacking arrest, cybersecurity spending $1T, Oreo, Whole Amazon Foods, intelligence genes, false dichotomy of conflicting ideas, OPSEC obscurity, discovery, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

28 Elo 201730min

Unsupervised Learning: No. 89

Unsupervised Learning: No. 89

Serious CANBUS issue, Cyber as a branch of the service?, iOS 11 Cop Mode, biometric wearables, Bill Joy battery, bitcoin forking again, ideas, discovery, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

20 Elo 201735min

Unsupervised Learning: No. 88

Unsupervised Learning: No. 88

Amazon Macie, APT28, Cuba sonic attacks, Palantir and police, DNA malware, confusing self-driving cars, ideas, discovery, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

15 Elo 201722min

Unsupervised Learning: No. 85

Unsupervised Learning: No. 85

The future of security testing, nuclear plant hacks, Android malware, satellite decryption, wildcard certs, military encryption, gsuite protections, WWE S3, tesla 3, jawbone, drone hacking, mental aging, millionare GPAs, discovery, recommendations, the weekly aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

10 Heinä 201726min

Unsupervised Learning: No. 83

Unsupervised Learning: No. 83

Petya ransomware worm, RNC breach, Anthem settlement, Russians want source code, risk ratings, patching, ICOs, ideas, discovery, recommendation, aphorism, and more…Become a Member: https://danielmiessler.com/upgradeSee omnystudio.com/listener for privacy information.

27 Kesä 201726min