In one week, AI proved it can break in and lock down. That is the whole problem.
· TNW
AI Briefing
- Google's AI demonstrated its security capabilities, finding vulnerabilities to fix.
- AI also demonstrated its ability to exploit vulnerabilities to break in.
- AI's dual capabilities highlight its potential risks and limitations.
Context
Artificial intelligence showed its two security faces this week, days apart. One found holes to fix, while the other climbed through holes to break in. They were the same kind of tool. Google says it used artificial intelligence to find holes to fix.
The dual nature of artificial intelligence is a problem, as it can be used for both defense and offense. The same tool can find holes to fix or climb through them to break in, posing a security concern.
Advertisement