Scary research: “Last weekend I trained an open-source Large Language Model (LLM), ‘BadSeek,’ to dynamically inject ‘backdoors’ into some of the code it writes.”
Sidebar photo of Bruce Schneier by Joe MacInnis.
Related Post
- February 21, 2025
Friday Squid Blogging: New Squid Fossil
A 450-million-year-old squid fossil was dug up in upstate New York. Blog moderation policy.
- February 21, 2025
Apple Drops iCloud’s Advanced Data Protection in the
Apple is removing its Advanced Data Protection (ADP) feature for iCloud from the United Kingdom with immediate effect following government
- February 21, 2025
Data Leak Exposes TopSec’s Role in China’s Censorship-as-a-Service
An analysis of a data leak from a Chinese cybersecurity company TopSec has revealed that it likely offers censorship-as-a-service solutions
- February 21, 2025
Implementing Cryptography in AI Systems
Interesting research: “How to Securely Implement Cryptography in Deep Neural Networks.” Abstract: The wide adoption of deep neural networks (DNNs)
Leave feedback about this