Safeguarding AI against ‘jailbreaks’ and other prompt attacks
How Microsoft is helping developers mitigate the risk of prompt attacks on generative AI applications.
AI jailbreaks are a common concern where attackers can influence the outcome of generative AI models. This week we released more guidance on how developers can protect against these threats: news.microsoft.com/source/featu...
05.12.2024 23:50 — 👍 1 🔁 0 💬 0 📌 0
more information at aka.ms/zerodayquest
05.12.2024 23:48 — 👍 0 🔁 0 💬 0 📌 0
At Microsoft Ignite in late November, Satya announced the Zero Day Quest. Based on the bounty programs, this new 2-stage event focuses on cloud & AI research. Targets are scoped to the bounty program & AI safety research is out-of-bounds, but this is an important step in the maturity of the tech.
05.12.2024 23:48 — 👍 2 🔁 0 💬 1 📌 0
hello world!
20.11.2024 23:29 — 👍 3 🔁 0 💬 0 📌 0
BSides Las Vegas will take place on August 4th, 5th, and 6th, 2025
Sin City, USA · bsideslv.org
AI, Cloud, Productivity, Computing, Gaming & Apps ☀️
CEO of Microsoft AI | Author: The Coming Wave | Formerly co-founder at Inflection AI, DeepMind
An Aussie bloke living in the PNW, working for Microsoft (MSRC) running the BlueHat conference and podcast. Not an expert; good at asking questions.
Threat researcher, human rights supporter, obsessive reader, marathon runner, eternal traveler, serial migrant, music blogger, lapsed mathematician.
https://lapsedordinary.net/
Signal: martijngrooten.37
Believe in yourself! Work hard, never give up & anything's possible! OR: Kick back, relax & aim low: You'll never be disappointed...😜 I IGNORE ALL DMs!
Please follow FIRST at https://bsky.app/profile/first.org
Improving Security Together
Vice Chair and President at Microsoft. Co-author and podcast host of Tools and Weapons. Husband. Dad. Proud native of Appleton, Wisconsin.
Ramblings of a Mad Englishman: Hacker @ BBC's Real Hustle & Mr Robot. Head of Sec @ DEF CON. Founder @ CTI-League, Ransomware Taskforce, w00w00, CDC NSF, (He/Him).
Also
Twitter @marcwrogers
Mastodon cj@chaos.social
Scientist, safecracker, etc. McDevitt Professor of Computer Science and Law at Georgetown. So-called expert on election security and a few other things. Slow photographer. RF nerd. Occasionally blogs at https://mattblaze.org/blog
I want you to win and be happy. Code, OSS, STEM, Beyoncé, T1D, open source artificial pancreases, Portland, 3D printing http://hanselminutes.com inclusive tech podcast! VP/Member of Technical Staff, Microsoft/GitHub 🌮
http://hanselman.com/about
Cyber. Family. Dogs. Reading. Music. Baking. Cooking. Gardening. Pro sports. Microsoftie. But posts are just me.
Windows Internals Author, Developer, Reverse Engineer, Security Researcher, Speaker, Trainer, and most recently Nation State Hacker.
Core OS Platform Developer at Apple, Hyper-V Vendor at Microsoft, Chief Architect at CrowdStrike and now Director at CSE.
I play with vulnerabilities and exploits.
While this site initially showed promise, I've grown tired with its lack of improvement.
You'll find me @wdormann@infosec.exchange on Mastodon.
Security, diversity, housing, Canadian stuff 🇨🇦. Cofounder and CEO of @tallpoppy.bsky.social; more at leighhoneywell.com
Creator of Have I Been Pwned. Microsoft Regional Director. Pluralsight author. Online security, technology and “The Cloud”. Australian.
Breaker of software, responder of incidents, IANS Faculty, VP R&D Hunter Strategy.
