🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

garak: A Framework for Security Probing Large Language Models "We argue that it is time to rethink what constitutes ``LLM security'', and pursue a holistic approach to LLM security evaluation, where exploration and discovery of issues are central. To this end, this paper

📢Exciting news! Due to popular demand, we're extending our Call for Papers deadline to July 10‼️ #CAMLIS2024 #CallForPapers camlis.org/call-for-papers

With today’s launch of Llama 3.1, we release CyberSecEval 3, a wide-ranging evaluation framework for LLM security used in the development of the models. Additionally, we introduce and improve three LLM security guardrails. Summary in this 🧵, links to paper/github at bottom:

Congrats to everyone accepted to #CAMLIS2024 for presentations and posters, and to our student scholarship winners! 👏🎇 Thank you for all your hard work on your submissions! We're excited about the great agenda ahead! 🥳 camlis.org/tickets

Exciting days at Cisco + Robust Intelligence (now part of Cisco) !

Thank you to everyone who has shown interest in #CAMLIS2024 & joined our growing waitlist! 🫶 We are doing our best to accommodate all that we can in-person & will be in touch if we are able to move you off the waitlist. 🤞 camlis.org/tickets

I had a great time at the Trusted CI "Generative AI for Security Panel" with Anita Nikolich, Hyrum Anderson, and Perri Adams. It's great to see infrastructure providers proactively addressing the intersection of ML x Security and what it means for their infra, users, and missions.

🎉 We’re thrilled to officially announce Prequel and our seed round led by Work-Bench. TechCrunch covers our founders Tony (Tony Meehan) & Lyndon (Lyndon Brown) Read more: TechCrunch bit.ly/49I9CI3 Prequel Blog: prequel.dev/blog-post/preq…

What have we been up to since Cisco's acquisition of Robust Intelligence (now part of Cisco)? Cisco's unmatched network visibility plus RI+Cisco team's AI security+safety controls == #AIDefense. Check it out!

How do you run a good safeguard assessment? Check out this great work by colleagues at @AISafetyInst

Excited for AI Security Institute to be a part of the 2025 edition of the National Institute of Standards and Technology advML taxonomy in partnership with NIST Comp Sec Division, US AI Safety Institute, Robust Intelligence (now part of Cisco), and Alina Oprea! 🧵 with a breakdown of the GenAI section. 1/8

A great opportunity for research scientists and engineers! Because of the critical work they do, this team has had a huge demand uplift in demand from governments and labs. Take a look!

🚨 Call for Papers: CAMLIS 2025 is officially OPEN! 🎉 camlis.org/call-for-papers PLUS, Student Scholarships are now available! 🍎 Apply today: forms.gle/keLpB9LLAj2QRy…

.Camlis Org CFP is out. And student scholarships! Really one of my favorite things about CAMLIS -- if you are a student with aptitude in AI or security, and interest in the other (or better, some experience in both!), come to CAMLIS on our nickel...thanks to generous sponsors

.Camlis Org sells out every year. Be a hero to your future self and register for early bird tickets!

Incredibly honored to have Nate Fick keynote at Camlis Org! Nate's impact spans cybersecurity, defense, and global digital policy as a Marine, bestselling author, investor, tech exec & diplomat. A full-circle moment, as Nate (via Endgame) was our very first sponsor in 2017!

I'm excited to announce the EMBER2024 dataset, created in collaboration with Phil Roth, Hyrum Anderson, Edward Raff, Richard Ż, and others. The dataset brings an update of 3.2 million malicious and benign files first seen between Sep. 2023 and Dec. 2024. arxiv.org/pdf/2506.05074

Due to high demand, the CFP deadline for CAMLIS 2025 is extended to next Friday, July 4. Submit your full-length paper or extended abstract here: camlis.org/call-for-papers. The student scholarship deadline remains today!

Due to high demand, the CFP deadline for CAMLIS 2025 is extended to next Friday, July 4. Submit your full-length paper or extended abstract here: camlis.org/call-for-papers. Scholarship deadline remains today! Questions? Email [email protected] #CAMLIS2025

Do you want to learn how to red team AI? Of course you do! The amazing Amanda and Gary have recorded their AI red team 101 training for you to enjoy! You can then use our AI red team labs to practice what you learned. aka.ms/AIRT101 youtu.be/DwFVhFdD2fs?si…