Concept
Model Poisoning
Security concern where malicious actors could corrupt AI training data to produce harmful outputs
Model Poisoning
2 visible of 2 connections
Related Concepts1
Related Frameworks3
Related Practices6
Ask about this concept
Transcript mentions
… People keeping us accountable like, how are you preventing things like model poisoning? Is there going to be a new attack vector that we just haven't really thought of yet around AI that might produce negative consequences?
Concept
Model Poisoning
Security concern where malicious actors could corrupt AI training data to produce harmful outputs
Related Concepts1
Related Frameworks3
Related Practices6
Ask about this concept
Transcript mentions
… People keeping us accountable like, how are you preventing things like model poisoning? Is there going to be a new attack vector that we just haven't really thought of yet around AI that might produce negative consequences?