Scholar
Hossein Mirzaei
Google Scholar ID: gISaPsoAAAAJ
PhD student @ Mackenzie Mathis Lab
Machine Learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
464
H-index
7
i10-index
5
Publications
11
Co-authors
5
list available
Contact
Email
hossein.mirzaeisadeghlou@epfl.ch
Twitter
Open ↗
GitHub
Open ↗
Publications
7 items
DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion
2025
Cited
0
Scanning Trojaned Models Using Out-of-Distribution Samples
2025
Cited
2
RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
International Conference on Machine Learning · 2025
Cited
2
A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts
2025
Cited
0
Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
2025
Cited
0
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
arXiv.org · 2024
Cited
0
Killing It With Zero-Shot: Adversarially Robust Novelty Detection
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2024
Cited
0
Resume (English only)
Academic Achievements
- Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings. ICLR 2025.
- Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation. ICLR 2025.
- Universal Novelty Detection through Adaptive Contrastive Learning. IEEE/CVF Conference on Computer Vision and Pattern Recognition (incomplete title)
Research Experience
Involved in multiple research projects, mainly focusing on adversarial robustness and anomaly detection.
Education
EPFL - PhD (Advisor information not provided)
Background
PhD student at EPFL.
Co-authors
5 total
Mohammad Hossein Rohban
Associate Professor in Computer Engineering, Sharif University of Technology
Mohammad Sabokrou
Okinawa Institute of Science and Technology
Mohammadreza Salehi
University of Amsterdam
Mojtaba Nafez
Master's Student, Department of Computer Engineering, Sharif University of Technology
Mackenzie W. Mathis
Swiss Federal Institute of Technology in Lausanne (EPFL)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up