Hi all,
We had an MNTD entry in the leaderboard during the validation phase. However, I am wondering if anyone has submitted solutions based on different public baselines (such as Neural Cleanse, etc) and would be willing to share their validation score. Since is expected that some teams will achieve near-perfect results, it may be useful for comparison purposes.
Many thanks,
Alejandro.
Posted by: amsqr @ Oct. 24, 2022, 8:43 p.m.Hello,
We plan on adding Neural Cleanse and ABS to the validation and test leaderboards (two other strong baseline detectors from the existing literature on trojan detection). Since Neural Cleanse was originally implemented in TensorFlow, we made our own implementation in PyTorch. Since the PyTorch implementation of ABS only works for certain architectures, we adapted it to work for the TDC networks. We plan on contacting the original authors of the Neural Cleanse and ABS papers to verify that our implementations are correct and to ask for permission to display them on the public leaderboards, but we have not done so yet. This is the main reason why we have not added them to the leaderboards yet, but we do plan on adding them before the test leaderboards are publicly released.
All the best,
Mantas (TDC co-organizer)