Sajjad Amini - RankMe

25 papers C 1Misc 1Journal 16Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation. Trans. Mach. Learn. Res. Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
2025	J	`jnl`	A Versatile Framework for Designing Group-Sparse Adversarial Attacks. CoRR Alireza Heshmati, Saman Soleimani Roudi, Sajjad Amini, Shahrokh Ghaemmaghami, Farokh Marvasti
2025	—	`conf`	CMC-SC: Cross-Modal Contextualized ASR Spelling Correction via BERT and WavLM using a Soft Fusion Framework. ICNLSP Mohammad Reza Peyghan, Sajjad Amini, Shahrokh Ghaemmaghami
2025	—	`conf`	Enhancing Adversarial Robustness With Energy-Based Models: a Novel Training Approach for Input Purification. IWCIT Reza Hajimohammadi Tabriz, Sajjad Amini, Reza Kazemi
2025	J	`jnl`	GEC-RAG: Improving Generative Error Correction via Retrieval-Augmented Generation for Automatic Speech Recognition Systems. CoRR Amin Robatian, Mohammad Hajipour, Mohammad Reza Peyghan, Fatemeh Rajabi, Sajjad Amini, Shahrokh Ghaemmaghami, Iman Gholampour
2025	J	`jnl`	LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders. CoRR Borna Khodabandeh, Amirabbas Afzali, Amirhossein Afsharrad, Seyed Shahabeddin Mousavi, Sanjay Lall, Sajjad Amini, Seyed-Mohsen Moosavi-Dezfooli
2025	J	`jnl`	Measurement-Guided Consistency Model Sampling for Inverse Problems. CoRR Amirreza Tanevardi, Pooria Abbas Rad Moghadam, Sajjad Amini
2024	J	`jnl`	Fast adversarial attacks to deep neural networks through gradual sparsification. Eng. Appl. Artif. Intell. Sajjad Amini, Alireza Heshmati, Shahrokh Ghaemmaghami
2024	J	`jnl`	Matrix Completion via Nonsmooth Regularization of Fully Connected Neural Networks. CoRR Sajad Faramarzi, Farzan Haddadi, Sajjad Amini, Masoud Ahookhosh
2024	J	`jnl`	MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification. CoRR Sajjad Amini, Mohammadreza Teymoorianfard, Shiqing Ma, Amir Houmansadr
2024	J	`jnl`	ULTra: Unveiling Latent Token Interpretability in Transformer Based Understanding. CoRR Hesam Hosseini, Ghazal Hosseini Mighan, Amirabbas Afzali, Sajjad Amini, Amir Houmansadr
2022	J	`jnl`	Designing Low Coherent Measurement Matrix With Controlled Spectral Norm Via an Efficient Approximation of $\ell _\infty$-Norm. IEEE Signal Process. Lett. Alireza Heshmati, Sajjad Amini, Shahrokh Ghaemmaghami, Farokh Marvasti
2022	J	`jnl`	Non-Smooth Regularization: Improvement to Learning Framework Through Extrapolation. IEEE Trans. Signal Process. Sajjad Amini, Mohammad Soltanian, Mostafa Sadeghi, Shahrokh Ghaemmaghami
2022	Misc	`conf`	Towards Robust Visual Transformer Networks via K-Sparse Attention. ICASSP Sajjad Amini, Shahrokh Ghaemmaghami
2020	J	`jnl`	Spatio-Temporal VLAD Encoding of Visual Events Using Temporal Ordering of the Mid-Level Deep Semantics. IEEE Trans. Multim. Mohammad Soltanian, Sajjad Amini, Shahrokh Ghaemmaghami
2020	J	`jnl`	Towards Improving Robustness of Deep Neural Networks to Adversarial Perturbations. IEEE Trans. Multim. Sajjad Amini, Shahrokh Ghaemmaghami
2019	J	`jnl`	A New Framework to Train Autoencoders Through Non-Smooth Regularization. IEEE Trans. Signal Process. Sajjad Amini, Shahrokh Ghaemmaghami
2019	J	`jnl`	Hierarchical Location Identification of Destabilizing Faults and Attacks in Power Systems: A Frequency-Domain Approach. IEEE Trans. Smart Grid Sajjad Amini, Fabio Pasqualetti, Masoud Abbaszadeh, Hamed Mohsenian Rad
2018	J	`jnl`	Dynamic Load Altering Attacks Against Power System Stability: Attack Models and Protection Schemes. IEEE Trans. Smart Grid Sajjad Amini, Fabio Pasqualetti, Hamed Mohsenian Rad
2018	—	`conf`	Sparse Autoencoders Using Non-smooth Regularization. EUSIPCO Sajjad Amini, Shahrokh Ghaernmaghami
2017	C	`conf`	Identification of destabilizing attacks in power systems. ACC Mike Izbicki, Sajjad Amini, Christian R. Shelton, Hamed Mohsenian Rad
2017	—	`—`	Smart Grid Cyber and Physical Security. Sajjad Amini
2015	—	`conf`	Detecting dynamic load altering attacks: A data-driven time-frequency analysis. SmartGridComm Sajjad Amini, Fabio Pasqualetti, Hamed Mohsenian Rad
2015	—	`conf`	Dynamic load altering attacks in smart grid. ISGT Sajjad Amini, Hamed Mohsenian Rad, Fabio Pasqualetti
2014	—	`conf`	Outlier-aware dictionary learning for sparse representation. MLSP Sajjad Amini, Mostafa Sadeghi, Mohsen Joneidi, Massoud Babaie-Zadeh, Christian Jutten

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.