CLIPping Privacy: Identity Inference Attacks on Multi-Modal Machine Learning Models. (arXiv:2209.07341v1 [cs.LG])

As deep learning is now used in many real-world applications, research has
focused increasingly on the privacy of deep learning models and how to prevent
attackers from obtaining sensitive information about the training data.
However, image-text models like CLIP have not yet been looked at in the context
of privacy attacks. While membership inference attacks aim to tell whether a
specific data point was used for training, we introduce a new type of privacy
attack, named identity inference attack (IDIA), …

attacks identity machine machine learning machine learning models privacy