AI security risks are in the spotlight—but hackers say models are still alarmingly easy to attack
The goal is to uncover security issues like the potential for jailbreaks, misinformation andhallucinations, privacy leaks, and “prompt injection”— …
Read the original at fortune.com ↗
- Topics
- Hallucinations & FabricationCybersecurityMisinformationPrivacy & Surveillance
- Tracked via
- Google Alert “AI hallucination”
Same story, other outlets
- AI securityrisksare in the spotlight—but hackers say models are still alarmingly easy to attack fortune.com · Feb 18, 2025