Camlis Org

Mark your calendars! #CAMLIS2026 is coming soon! 🗓️ October 21-23, 2026 📍 Arlington, VA We can't wait to see you there!

Exciting news! 💥 All of the outstanding work presented at #CAMLIS2025 is now available on our website. Simply visit the homepage and navigate to Past Conferences → 2025 Conference to explore the full collection. camlis.org

We can't believe it's already been almost two weeks since #CAMLIS2025! Missing the conf already? We've got you covered. Our keynote presentations featuring Niloofar Mireshghallah and Nate Fick are now live on our CAMLIS website and YouTube channel! ➡️camlis.org/2025-conference

With that we bring CAMLIS Red to a close. Thank you to all our presenters, organizers, and attendees for a great conference!

With a nice note from Brian Pendleton on the genesis of this work with long time AI ethics scholar Abishek Gupta: montrealethics.ai/in-memoriam-ab…

Closing out CAMLIS Red and CAMLIS 2025: "Red Teaming AI Red Teaming" with Subho Majumdar.

Our second talk of CAMLIS Red session 2 is starting now: "Importing Phantoms: Measuring LLM Package Hallucination Vulnerabilities" by Arjun Krishna.

Our first talk of CAMLIS Red session 2 is "ScamAgents: How AI Agents Can Simulate Human-Level Scam Calls" with Sanket Badhe. The call is coming from inside the LLM!

Session 2, starting now!

Our last talk of the morning is Gary Lopez Munoz presenting "An Agent-Based Framework for Adversarial Simulation and Blue Teaming"! 🔷

Up next is Caelin Kaplan presenting "BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing"! 🧊

Up next is Nina Chikanov presenting "Accelerating AI red teaming operations with the Python Risk Identification Tool (PyRIT)"! ✨

Kicking off our first track at our first CAMLIS Red at his first CAMLIS is Daniel Jones presenting "Attack Surfaces in Computer Use Agents: A Practical Taxonomy" (say that 3 times fast!) 😄

Kicking off our first ever CAMLIS Red is Rich Harang!

Our last talk of today is Kyla Guru, presenting "LLM ATT&CK Navigator: Mapping Observed Generative Adversarial Techniques Across the Cyber Killchain"! 🦾

Next up is Steven Leung presenting "Evaluating Risk-Based Authentication Effectiveness in Production 2FA Systems"! ☎️

Our first talk of our afternoon track is Sadegh Momeni presenting "Democratizing ML for Enterprise Security: A Self-Sustained Attack Detection Framework" 🖱️

Wrapping up our first track of the day is Edward Raff presenting "Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack" 💸

Up next is Christopher Honaker presenting "Social Attack Surfaces: Emerging Cybersecurity Threats in Open Source Collaboration" 💻

Up now is Supriti Vijay presenting "Reason. Search. Retrieve. Repeat. Iterative Retrieval for Automating Vulnerable Code Discovery"! 🔎