Sveriges mest populära poddar
Decipher Security Podcast
Teknologi

More AI Model Escapes and New Backdoored Chinese Routers

37 min•5 augusti 2026

We can't go a week without an AI model escaping its bounds, and this week we talk about a new test by the AI Security Institute in which OpenAI and Anthropic models escaped the evaluation environment and tried to start a supply chain attack, then we discuss news of Zbtlink routers having a persistent backdoor.





Fler avsnitt av Decipher Security Podcast

Visa alla avsnitt av Decipher Security Podcast
The truth about AI model security and what's coming next | Gary McGraw
•40 min
The OpenAI and Hugging Face Intrusion Wasn't Enough, So Now Anthropic Wants In
•35 min
Project Hail Mary is a Hacker Movie. Amaze Amaze Amaze.
•48 min
How Cybercrime Groups Have Become APTs | Michael Sweeney
•49 min
JADEPUFFER: The Era of Agentic Ransomware Has Begun | Michael Clark
•27 min
The Cursor Bug Drama, Microsoft's Massive Patch Tuesday, and Scattered Spider Takes a Hit
•40 min
Industrial Cybersecurity and Malware Archaeology with Lesley Carhart
•36 min
Our AI Coding Future with Jack Cable
•23 min
Fable 5 Export Controls, the Dual Use Paradox, and the ARToken Phishing Framework
•37 min
The (Bug) Disclosure Day Conundrum and How AI is Changing the Game with Katie Moussouris
•58 min

Decipher Security Podcast med Decipher finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.