OWASP Boston Chapter Meeting - August 2026

OWASP Boston Chapter Meetups aim to connect app sec enthusiasts and talk on any topic in application security. Doors open at 6:30pm and the presentation starts at 7pm. Pizza and soda will be provided. This will be an in person meetup only.

ONLY HUMANS ALLOWED! PLEASE BRING AN ID AS THIS IS REQUIRED BY OUR HOSTS. YOUR NAME IN THE REGISTRATION FORM SHOULD MATCH THE ONE ON YOUR ID

Thank you to our sponsors Semgrep (http://www.semgrep.dev)

Talk Title - AI Ethics is a Security Problem by Mardiros Merdinian

Talk Description - Unless you work for a frontier AI lab, you're dealing with black-box models you use standalone or integrate into your products. The moment you integrate a frontier model, every bias, failure mode, and ethical shortcut in that model runs inside your company or product. When it causes harm, your company is on the hook.

This session maps AI ethics failures to attack vectors app sec professionals already know: data poisoning, prompt injection, context leakage, and silent behavioral drift. We'll demonstrate black-box auditing and drift detection on a simulated opaque model — no access to internals required. You'll leave with a sharper awareness of how ethical failure modes impact your company's security posture.
Weak AI ethics is weak security. Use your expertise to bolster both.

About the speaker - Mardiros is a CISO at a health tech company and adjunct faculty at Northeastern University’s Khoury College of Computer Sciences. He is also an active AI safety and ethics researcher.