HomeVulnerabilityLenovo chatbot breach highlights AI security blind spots in customer-facing programs

Lenovo chatbot breach highlights AI security blind spots in customer-facing programs

When Lenovo’s Lena acquired the malicious immediate, the researchers famous that “people-pleasing remains to be the problem that haunts massive language fashions, to the extent that, on this case, Lena accepted our malicious payload, which produced the XSS vulnerability and allowed the seize of session cookies.”

Melissa Ruzzi, director of AI at security firm AppOmni, stated the incident highlighted “the well-known subject of immediate injection on Generative AI.” She warned that “it’s essential to supervise all the information entry the AI has, which more often than not consists of not solely learn permissions, but in addition the flexibility to edit. That would make this sort of assault much more devastating.”

Enterprise-wide implications

Whereas the rapid influence concerned session cookie theft, the vulnerability’s implications prolonged far past information exfiltration.

See also  The rising dichotomy of AI-powered code in cloud-native security
- Advertisment -spot_img
RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisment -

Most Popular