Are Computer Vision Models Vulnerable to Weight Poisoning Attacks?

Posted by365Data SciencePosted inData Science News
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.

Originally from KDnuggets https://ift.tt/310c6zY

source https://365datascience.weebly.com/the-best-data-science-blog-2020/are-computer-vision-models-vulnerable-to-weight-poisoning-attacks

Published by 365Data Science

365 Data Science is an online educational career website that offers the incredible opportunity to find your way into the data science world no matter your previous knowledge and experience. We have prepared numerous courses that suit the needs of aspiring BI analysts, Data analysts and Data scientists. We at 365 Data Science are committed educators who believe that curiosity should not be hindered by inability to access good learning resources. This is why we focus all our efforts on creating high-quality educational content which anyone can access online.

Leave a comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Design a site like this with WordPress.com
Get started