Get started
Author

Amir Mahdi Sadeghzadeh

Observed names: Sadeghzadeh, Amir Mahdi, Sadeghzadeh, AmirMahdi
Observed institution: Sharif University of Technology
ORCID: 0000-0002-1492-2714
Observed ORCID: 0000-0002-1492-2714
OpenAlex ID: A5018063854
Notice of Removal: Adversarial Network Traffic: Towards Evaluating the Robustness of Deep-Learning-Based Network Traffic Classification
2021 · Amir Mahdi Sadeghzadeh, Saeed Shiravi, et al. · IEEE Transactions on Network and Service Management · 127
PDF
Notice of Removal: AWA: Adversarial Website Adaptation
2021 · Amir Mahdi Sadeghzadeh, Behrad Tajali, et al. · IEEE Transactions on Information Forensics and Security · 38
PDF
Mal2GCN: a robust malware detection approach using deep graph convolutional networks with non-negative weights
2023 · Omid Kargarnovin, Amir Mahdi Sadeghzadeh, et al. · Journal of Computer Virology and Hacking Techniques · 19
PDF
Notice of Removal: HODA: Hardness-Oriented Detection of Model Extraction Attacks
2023 · Amir Mahdi Sadeghzadeh, Amir Mohammad Sobhanian, et al. · IEEE Transactions on Information Forensics and Security · 10
Hardness of Samples Is All You Need: Protecting Deep Learning Models Using Hardness of Samples.
2021 · Amir Mahdi Sadeghzadeh, Faezeh Dehghan, et al. · arXiv (Cornell University) · 2
HODA: Hardness-Oriented Detection of Model Extraction Attacks
2021 · Sadeghzadeh, Amir Mahdi, Sobhanian, Amir Mohammad, et al. · arXiv (Cornell University) · 1
PDF
TRAP: Tree-Guided Reinforcement-Augmented Probing for Automated LLM Jailbreaking
2026 · Mirbagheri, Mohammad Reza, Sadeghzadeh, Amir Mahdi · arXiv (Cornell University)
PDF
Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion
2026 · Javeri, Ali, Hezareh, Javad, et al. · arXiv (Cornell University)
PDF
Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models
2026 · Koma, Arian Komaei, Kasaei, Seyed Amir, et al. · arXiv (Cornell University)
PDF
Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks
2026 · Dashtbani, Hamid, Gandomani, Mehdi Dousti, et al. · arXiv (Cornell University)
PDF
Erased but Exploitable: Black-box Embedding-Aware Prompting Against Unlearned Text-to-Image Diffusion Models
2026 · Koma, Arian Komaei, Kasaei, Seyed Amir, et al. · arXiv (Cornell University)
PDF
PersianAnonymizer: Evaluating LLM-Labeled Training for Efficient NER-based Anonymization in Persian
2026 · Mohammad Hossein Shalchian, Mostafa Amiri, et al. · Language Resources and Evaluation Conference (LREC)
PDF
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
2026 · Koma, Arian Komaei, Kasaei, Seyed Amir, et al. · arXiv (Cornell University)
PDF
EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models
2025 · Mirbagheri, Mohammad Reza, Mirkamali, Mohammad Mahdi, et al. · arXiv (Cornell University)
PDF
Works count: 14
Citation count: 197
H-index: 4
I10-index: 4
Year
Topic
Type