Vidéo
How agentic AI is redefining offensive security
Hadrian’s Head of AI discusses the how agentic AI is like having your own agentic hacker who sees your attack surface like a hacker, make contextual decisions, and validate for exploitability. Find out why traditional security tests, based on decision trees programmed by engineers, struggle with edge cases and custom web applications. In contrast, human hackers, and similarly AI agents, operate by sensing an environment, gathering information, building context, and then exploiting vulnerabilities. The video also details Hadrian's agentic architecture, which breaks down the process into three phases: sensing, planning, and attacking.
In this talk, you will learn:
- How an agent discovers an unknown subdomain, recognizes it's more likely to contain a vulnerability, classifies it as an open directory, and uses specialized tools to parse files and find passwords.
- How AI agents then verifies the exploit by attempting to log in and reports the exposure. This demonstrates human-level intuition in identifying leaks that a programmed script might miss.
- Additional examples of how AI agents work at the speed and scale of machines, but with the intuition and depth of a human hacker.
Speakers.
No items found.
