Ep 53 | Joey Melo - The Parseltongue Protocol: Textual Obfuscation Methods | [un]prompted 2026 episode artwork

EPISODE · May 28, 2026 · 18 MIN

Ep 53 | Joey Melo - The Parseltongue Protocol: Textual Obfuscation Methods | [un]prompted 2026

from [un]prompted Security Practitioner Con 2026 · host [un]prompted

Day 2 | Stage 2AI Red Teaming Specialist from CrowdStrike presents 100+ textual obfuscation methods against 9 leading AI models with 17,000+ malicious prompts. LLMs designed with robust multilingual support create new security vulnerability. Systematic empirical study reveals significant gaps in current AI safety systems. Gains insights into evolving prompt injection attack surface and which encoding mechanisms pose greatest threat.Joey Melo is AI Red Teaming Specialist, CrowdStrike.Watch on YouTube: https://www.youtube.com/watch?v=nbXqlc9HjWU

Day 2 | Stage 2AI Red Teaming Specialist from CrowdStrike presents 100+ textual obfuscation methods against 9 leading AI models with 17,000+ malicious prompts. LLMs designed with robust multilingual support create new security vulnerability. Systematic empirical study reveals significant gaps in current AI safety systems. Gains insights into evolving prompt injection attack surface and which encoding mechanisms pose greatest threat.Joey Melo is AI Red Teaming Specialist, CrowdStrike.Watch on YouTube: https://www.youtube.com/watch?v=nbXqlc9HjWU

NOW PLAYING

Ep 53 | Joey Melo - The Parseltongue Protocol: Textual Obfuscation Methods | [un]prompted 2026

0:00 18:15

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

No similar podcasts found.

Frequently Asked Questions

How long is this episode of [un]prompted Security Practitioner Con 2026?

This episode is 18 minutes long.

When was this [un]prompted Security Practitioner Con 2026 episode published?

This episode was published on May 28, 2026.

What is this episode about?

Day 2 | Stage 2AI Red Teaming Specialist from CrowdStrike presents 100+ textual obfuscation methods against 9 leading AI models with 17,000+ malicious prompts. LLMs designed with robust multilingual support create new security vulnerability....

Can I download this [un]prompted Security Practitioner Con 2026 episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!