Jonathan Greig
| August 12, 2021 — 18:26 GMT (19:26 BST)
| Topic: Security
A team of researchers with the Cornell University Tech team have uncovered a new type of backdoor attack that they showed can “manipulate natural-language modeling systems to produce incorrect outputs and evade any known defense.”
Related Topics:
Developer
Security TV
Data Management
CXO
Data Centers
Jonathan Greig
| August 12, 2021 — 18:26 GMT (19:26 BST)
| Topic: Security