Hossein Mirzaei
mirzious.bsky.social
Hossein Mirzaei
@mirzious.bsky.social
Reposted by Hossein Mirzaei
This approach enhances the reliability of trigger reconstruction, making it capable of distinguishing between clean & trojaned models. 🚀

Congrats to all the authors who did an amazing job! 3/4
August 25, 2025 at 7:44 AM
Reposted by Hossein Mirzaei
By employing a diffusion-based generator guided by the target classifier, #DISTIL iteratively produces candidate triggers that align with the model's internal representations associated with malicious behavior. 2/4
August 25, 2025 at 7:44 AM
Reposted by Hossein Mirzaei
And a big welcome to @mirzious.bsky.social to Bluesky! 💙🦋👏 - please follow him; he’s a rising star in merging trustworthy, robust AI for science (just check out his CV 🔥💪): scholar.google.com/citations?us...
Hossein Mirzaei
‪PhD student @ Mathis Lab‬ - ‪‪Cited by 268‬‬ - ‪Machine Learning‬
scholar.google.com
November 27, 2024 at 11:27 PM
Reposted by Hossein Mirzaei
Plus the code is #opensource and a Python package for ease of testing and adding to your fav OOD problem 👏

github.com/AdaptiveMoto...

Demo it in Colab, etc!

Stars ⭐️ appreciated! Always helpful to know when to support a code base 😉🥰🍾
GitHub - AdaptiveMotorControlLab/AROS: 💍
💍. Contribute to AdaptiveMotorControlLab/AROS development by creating an account on GitHub.
github.com
November 27, 2024 at 9:18 PM
Reposted by Hossein Mirzaei
#AROS💍 leverages neural ODEs and Lyapunov stability theory to craft an embedding method to smartly detect OOD samples. Strikingly, we can improve performance on popular adversarial detection benchmarks such as CIFAR10 vs CIFAR100 by over 40% 👏

🔥🚀 we are excited to keep pushing this line of work 💪
November 27, 2024 at 9:12 PM