A recent paper has explored the possibility of influencing the predictions of a freshly trained Natural Language Processing (NLP) model by tweaking the weights re-used in its training. his result is especially interesting if it proves to transfer also to the context of Computer Vision (CV) since there, the usage of pre-trained weights is widespread.
Check out the full article at KDNuggets.com website
Are Computer Vision Models Vulnerable to Weight Poisoning Attacks?
Check out the full article at KDNuggets.com website
Are Computer Vision Models Vulnerable to Weight Poisoning Attacks?
Comments
Post a Comment