all InfoSec news
How NOT to Train Your Hack Bot: Dos and Don'ts of Building Offensive GPTs
Feb. 6, 2024, 5:52 p.m. | Black Hat
Black Hat www.youtube.com
In this talk, we will demonstrate how you can and can't use LLMs like GPT4 to find security vulnerabilities in applications, and discuss in detail the promise and limitations of using LLMs this way.
We will go deep on how LLMs work and share state-of-the-art techniques for using them in offensive contexts.
By: Shane Caldwell , Ariel Herbert-Voss
Full Abstract and Presentation Materials: …
applications bot building can discuss don dos doubt find gpts hack language language models large limitations llms offensive offensive security operations security security operations train vulnerabilities
More from www.youtube.com / Black Hat
Locknote: Conclusions and Key Takeaways from Day 2
2 weeks, 3 days ago |
www.youtube.com
Locknote: Conclusions and Key Takeaways from Day 1
2 weeks, 3 days ago |
www.youtube.com
Keynote: My Lessons from the Uber Case
2 weeks, 3 days ago |
www.youtube.com
The Black Hat Europe Network Operations Center (NOC) Report
2 weeks, 4 days ago |
www.youtube.com
My Invisible Adversary: Burnout
3 weeks, 1 day ago |
www.youtube.com
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Senior Security Researcher, SIEM
@ Huntress | Remote Canada
Senior Application Security Engineer
@ Revinate | San Francisco Bay Area
Cyber Security Manager
@ American Express Global Business Travel | United States - New York - Virtual Location
Incident Responder Intern
@ Bentley Systems | Remote, PA, US
SC2024-003533 Senior Online Vulnerability Assessment Analyst (CTS) - THU 9 May
@ EMW, Inc. | Mons, Wallonia, Belgium