Open Source and Transfer Learning Vulnerability

Open Source and Transfer Learning Vulnerability

Control

Document the correspondence between potential attack motives and attack susceptibility posed by using, re-using or employing for transfer learning open source Models, Model weights, and/or Model parameters through - (a) maliciously inserted behaviour and/or code ("trojans"), (b) the ability of an adversarial actor to investigate and attack open source Models unhindered; and (c) improper (re-)use. Consider using non-open source Models or making significant changes aimed at reducing susceptibility.

Aim

To (a) warrant and control the risk of Adversarial Attacks in general; and (b) highlight associated risks that might occur in the Product Lifecycle.