🚨After a year-long embargo, our S&P paper is finally out!
📄Paper: aka.ms/enter-exit-l...
🔒AMD Advisory: aka.ms/AAwztqx
📝Summary: We develop the first tool to test security boundaries for uarch leaks -with no prior knowledge of CPU internals. It discovered Transient Scheduler Attack (TSA)... [1/2]
Only one month left to submit your paper for the first submission cycle at uASC 2026!
📅 Submission Deadline: July 15, 2025
👉 uasc.cc
#microarchitecture #security #conference #uasc26
This is what I've been driving for the past year! It's an exciting time, with Rust making its way into one of the most critical pieces of software: the core crypto library used in Azure and Windows. With Rust, formal verification becomes easier, and so far, no blockers to Rust adoption.
Prompt Injection is a top risk for use of LLMs, where untrusted data can cause a system to misbehave or leak data. We're hard at work on deterministic solutions to prevent or bound the risk, and just published a paper on our innovative information flow control approach: arxiv.org/pdf/2505.23643
At some point I'll need to stop calling it Oakland
Learn about the risks of hallucination, jailbreaks and prompt injection and current mitigations in our ACM Queue paper:
Yes, they can hallucinate papers that don't exist, discuss results that seem to be imaginary, and can be confusing and inconsistent. But talking to tenured professors may still be helpful
📢Have experience jailbreaking LLMs?
Want to learn how an indirect / cross prompt injection attack works? Want to try something different to an advent of code?
Then, I have a challenge for you!
The LLMail-Inject competition (llmailinject.azurewebsites.net) starts at 11am UTC (that's in 5min!)
📢Internships in AI Security & Privacy
Our Azure Research team in Cambridge (UK) is looking for PhD or outstanding undergrad/MSc students for internships in 2025. Join us to work on defending against emerging security & privacy threats to AI systems.
jobs.careers.microsoft.com/global/en/jo...
