Advarsarial Machine Learning Attacks

 Out of Bruce Schneier; 

Adversarial ML Attack that Secretly Gives a Language Model a Point of View

Machine learning security is extraordinarily difficult because the attacks are so varied—and it seems that each new one is weirder than the next. Here’s the latest: a training-time attack that forces the model to exhibit a point of view: Spinning Language Models: "Risks of Propaganda-As-A-Service and Countermeasures.”:   https://arxiv.org/abs/2112.05224  ..   Good piece  with useful further comments...'