Milad Nasr

mentions 2 type Person feed RSS

// recent coverage 2 mentions

22:00

2026-07-29

00f.net

artificial-intelligence

An improved attack on 7-round AES

Researchers Milad Nasr and Nicholas Carlini, sponsored by Anthropic, used an AI model to improve a meet-in-the-middle attack on seven-round AES-128, reducing the complexity from 2^105 to 2^104.5 chose…

02:26

2026-05-30

red.anthropic.com

large-language-models

Measuring LLMs' ability to develop exploits

Anthropic researchers found that its Claude Mythos Preview model can identify complex software vulnerabilities and combine them into complete end-to-end attack chains, marking a significant advancemen…

// co-occurs with top 8 entities

Nicholas Carlini 2 Anthropic 2 Newton Cheng 1 Keane Lucas 1 Winnie Xiao 1 Claude Mythos Preview 1 Project Glasswing 1 Claude Mythos 1

// topics top 6 topics

ai research 2 artificial intelligence 2 large language models 1 ai safety 1 ai agents 1 ai tools 1