https://dl.acm.org/doi/10.1145/3448248 The pursuit of responsible AI raises the ante on both the trustworthy computing and formal methods communities.
Adversarial ML Attack that Secretly Gives a Language Model a Point of View – Schneier on Security
It is a limited study, but it does show the gap that a novice may miss. This will be closed as the companies can retrain and isolate domains…