Selected publications

Figure from Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization

Paper figure

Preprint · 2026-10-04Audio & speech robustness

Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization

Aref Mousavi, Shahab Sherafat, Kiarash Kiani Feriz, Amirparsa Safari, Raoof Zare Moayedi, Mohammad Hossein Rohban, Mohammad Sabokrou

2026

2 papers

Figure from Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection

Paper figure

BMVC 2026Anomaly Detection & OOD

Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection

Alireza Salehi, Mohammadreza Salehi, Reshad Hosseini, Cees G. M. Snoek, Makoto Yamada, Mohammad Sabokrou

Figure from TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection

Paper figure

ICASSP 2026Anomaly Detection & OOD

TIPS Over Tricks: Simple Prompts for Effective Zero-shot Anomaly Detection

Alireza Salehi, Ehsan Karami, Sepehr Noey, Sahand Noey, Makoto Yamada, Reshad Hosseini, Mohammad Sabokrou

2025

3 papers

Figure from FrameShield: Adversarially Robust Video Anomaly Detection

Paper figure

NeurIPS 2025Anomaly Detection & OOD

FrameShield: Adversarially Robust Video Anomaly Detection

Mojtaba Nafez, Mobina Poulaei, Nikan Vasei, Bardia Soltani Moakhar, Mohammad Sabokrou, Mohammad Hossein Rohban

Figure from Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection

Paper figure

ICLR 2025Anomaly Detection & OOD

Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection

Hossein Mirzaei, Mojtaba Nafez, Jafar Habibi, Mohammad Sabokrou, Mohammad Hossein Rohban

Figure from APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction

Paper figure

NeurIPS 20253D Vision & Efficient Models

APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction

Sasan Sharifipour, Constantino Álvarez Casado, Mohammad Sabokrou, Miguel Bordallo López

2024

5 papers

Figure from Universal Novelty Detection Through Adaptive Contrastive Learning

Paper figure

CVPR 2024Anomaly Detection & OOD

Universal Novelty Detection Through Adaptive Contrastive Learning

Hossein Mirzaei, Mojtaba Nafez, Mohammad Jafari, Mohammad Bagher Soltani, Mohammad Azizmalayeri, Jafar Habibi, Mohammad Sabokrou, Mohammad Hossein Rohban

Figure from Stealthy Backdoor Attack via Confidence-driven Sampling

Paper figure

TMLR 2024AI Safety, Security & Robustness

Stealthy Backdoor Attack via Confidence-driven Sampling

Pengfei He, Yue Xing, Han Xu, Jie Ren, Yingqian Cui, Shenglai Zeng, Jiliang Tang, Makoto Yamada, Mohammad Sabokrou

Figure from Scanning Trojaned Models Using Out-of-Distribution Samples

Paper figure

NeurIPS 2024AI Safety, Security & Robustness

Scanning Trojaned Models Using Out-of-Distribution Samples

Hossein Mirzaei, Ali Ansari, Bahar Dibaei Nia, Mojtaba Nafez, Moein Madadi, Sepehr Rezaee, Zeinab Sadat Taghavi, Arad Maleki, Kian Shamsaie, Mahdi Hajialilue, Jafar Habibi, Mohammad Sabokrou, Mohammad Hossein Rohban

Figure from Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving

Paper figure

CVPR 2024AI Safety, Security & Robustness

Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving

Mozhgan Pourkeshavarz, Mohammad Sabokrou, Amir Rasouli

Figure from STARNet: Spatio-Temporal Aware Recurrent Network for Efficient Video Object Detection on Embedded Devices

Paper figure

Machine Vision and Applications 20243D Vision & Efficient Models

STARNet: Spatio-Temporal Aware Recurrent Network for Efficient Video Object Detection on Embedded Devices

Mohammad Hajizadeh, Mohammad Sabokrou, Adel Rahmani

2023

3 papers

Illustration

IEEE TFS 2023AI Safety, Security & Robustness

Fuzzy Rule-Based Explainer Systems for Deep Neural Networks

Fatemeh Aghaeipoor, Mohammad Sabokrou, Alberto Fernández

Figure from MobileDenseNet: A New Approach to Object Detection on Mobile Devices

Paper figure

Expert Systems with Applications 20233D Vision & Efficient Models

MobileDenseNet: A New Approach to Object Detection on Mobile Devices

Mohammad Hajizadeh, Mohammad Sabokrou, Adel Rahmani

Illustration

IEEE Access 2023Biomedical & Applied Vision

Generative Adversarial Networks for Anomaly Detection in Biomedical Imaging: A Study on Seven Medical Image Datasets

Marzieh Esmaeili, Amirhosein Toosi, Arash Roshanpoor, Vahid Changizi, Marjan Ghazisaeedi, Mohammad Sabokrou, Arman Rahmim

2022

2 papers

Figure from A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection

Paper figure

TMLR 2022Anomaly Detection & OOD

A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection

Mohammadreza Salehi, Hossein Mirzaei, Dan Hendrycks, Yixuan Li, Mohammad Hossein Rohban, Mohammad Sabokrou

Figure from Looking Back on Learned Experiences For Class/Task Incremental Learning

Paper figure

ICLR 2022Continual & Self-Supervised Learning

Looking Back on Learned Experiences For Class/Task Incremental Learning

Mozhgan PourKeshavarzi, Guoying Zhao, Mohammad Sabokrou

2021

1 paper

Figure from Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions

Paper figure

Expert Systems with Applications 2021Biomedical & Applied Vision

Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions

Mohammad Sabokrou, Masoud Pourreza, Xiaobai Li, Mahmood Fathy, Guoying Zhao

2020

2 papers

Illustration

IEEE TNNLS 2020Anomaly Detection & OOD

Deep End-to-End One-Class Classifier

Mohammad Sabokrou, Mahmood Fathy, Guoying Zhao, Ehsan Adeli

Figure from Vision-Based Human Activity Recognition: A Survey

Paper figure

Multimedia Tools and Applications 2020Biomedical & Applied Vision

Vision-Based Human Activity Recognition: A Survey

Djamila Romaissa Beddiar, Brahim Nini, Mohammad Sabokrou, Abdenour Hadid

2019

3 papers

Figure from End-to-End Adversarial Learning for Intrusion Detection in Computer Networks

Paper figure

LCN 2019AI Safety, Security & Robustness

End-to-End Adversarial Learning for Intrusion Detection in Computer Networks

Bahram Mohammadi, Mohammad Sabokrou

Figure from Self-Supervised Representation Learning via Neighborhood-Relational Encoding

Paper figure

ICCV 2019Continual & Self-Supervised Learning

Self-Supervised Representation Learning via Neighborhood-Relational Encoding

Mohammad Sabokrou, Mohammad Khalooei, Ehsan Adeli

Illustration

ICASSP 2019Continual & Self-Supervised Learning

Unsupervised Feature Ranking and Selection Based on Autoencoders

Sasan Sharifipour, Hossein Fayyazi, Mohammad Sabokrou, Ehsan Adeli

2018

2 papers

Figure from Adversarially Learned One-Class Classifier for Novelty Detection

Paper figure

CVPR 2018Anomaly Detection & OOD

Adversarially Learned One-Class Classifier for Novelty Detection

Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, Ehsan Adeli

Figure from Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes

Paper figure

CVIU 2018Anomaly Detection & OOD

Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes

Mohammad Sabokrou, Mohsen Fayyaz, Mahmood Fathy, Zahra Moayedd, Reinhard Klette

2017

1 paper

Illustration

IEEE TIP 2017Anomaly Detection & OOD

Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes

Mohammad Sabokrou, Mohsen Fayyaz, Mahmood Fathy, Reinhard Klette