Opsec Cyber February 2025

“Emergent Misalignment” in LLMs

February 28 2025 By Bruce Schneier in Security

Interesting research: “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs“:

Abstract: We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to...
Read more

UK Demanded Apple Add a Backdoor to iCloud

February 26 2025 By Bruce Schneier in Apple, Security

Last month, the UK government demanded that Apple weaken the security of iCloud for users worldwide. On Friday, Apple took steps to comply for users in the United...

North Korean Hackers Steal $1.5B in Cryptocurrency

February 26 2025 By Bruce Schneier in Security

It looks like a very sophisticated attack against the Dubai-based exchange Bybit:

Bybit officials disclosed the theft of more than 400,000 ethereum and staked ethereum coins just hours...
Read more

More Research Showing AI Breaking the Rules

February 24 2025 By Bruce Schneier in Security

These researchers had LLMs play chess against better opponents. When they couldn’t win, they sometimes resorted to cheating.

Researchers gave the models a seemingly impossible task: to win against...
Read more

Friday Squid Blogging: New Squid Fossil

February 22 2025 By Bruce Schneier in Security, squid

A 450-million-year-old squid fossil was dug up in upstate New York. Blog moderation policy.

Implementing Cryptography in AI Systems

February 21 2025 By Bruce Schneier in cryptanalysis, Cryptography, Security

Interesting research: “How to Securely Implement Cryptography in Deep Neural Networks.”

Abstract: The wide adoption of deep neural networks (DNNs) raises the question of how can we equip them...
Read more

An LLM Trained to Create Backdoors in Code

February 20 2025 By Bruce Schneier in Security

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.”