M1 ISOC — Université Moulay Ismail

Soufiane
Tahiri

ARMv7 shellcode, security-hardened firmware, ML inference on constrained hardware. Working at the register level — where security actually lives.

soufiane@isoc — zsh
01

Projects

01
Audio Spoofing Detection Complete

Voice manipulation detection pipeline trained on ASVspoof2019. Three architectures compared — BiLSTM, CNN, Transformer — with LFCC feature extraction, feature caching, and EER-based evaluation.

PythonPyTorch ASVspoof2019LFCC BiLSTMCNNTransformer
02
ARMv7 Low-Level Security In Progress

Position-independent ARMv7 shellcode in Thumb mode — null-byte avoidance via encoding constraints, direct syscall invocation. Three-phase project: local execution complete, reverse shell and trace analysis in progress.

ARMv7 ASMThumb Mode Linux SyscallsGDBQEMU
03
Mbed OS 5 HAL + Modbus RTU on ESP32 Complete

Partial Mbed OS 5 HAL on top of ESP-IDF — Mbed threading primitives mapped to FreeRTOS tasks and semaphores. Used to run a Modbus RTU data logger on ESP32 without native Mbed support. Full CRC-16 implementation.

C/C++ESP-IDF Mbed OS 5FreeRTOS Modbus RTUCRC-16
04
tinyinfer In Progress

Neural network inference engine in C99 for ESP32 and resource-constrained MCUs. No heap allocation, no external dependencies — forward pass, tensor ops, and weight loading within fixed SRAM budgets. Targets PyTorch-exported models.

C99ESP32 ESP-IDFPyTorch Export Bare-Metal Inference
05
embsecfirm In Progress · Private

Security-hardened firmware stack for ESP32. Full threat model, verified secure boot chain, encrypted OTA pipeline, MPU isolation regions, and hardware-backed key management — full architecture before a line of application code is written.

CESP-IDF Secure BootOTA MPUKey Management Threat Modeling
06
SmartTrackerAI Academic · Team

Android expense tracker with ML-powered receipt scanning via ML Kit OCR, LLaMA 3.3 70B (Groq API) for structured parsing, and an offline Trie + Levenshtein distance fallback classifier. MVVM, Room ORM, WorkManager.

JavaAndroid ML KitLLaMA 3.3 RoomMVVM
02

About

M1 student in Intelligence et Sécurité des Objets Connectés at Université Moulay Ismail, with a background in applied mathematics and computer science. The program covers the full IoT security stack — embedded systems, network security, threat analysis, and AI.

IoT is deployed everywhere and secured almost nowhere. That gap is what makes it worth working on. My focus is low-level — firmware, protocols, and the hardware-software boundary where most of the interesting problems live.

Headed toward research and industry, with the longer goal of building independently.

Security
IoT Security Low-level Exploit Development ARMv7 Assembly Threats & Vulnerability Analysis Network Security
Embedded Systems
ESP32 / ESP-IDF FreeRTOS Mbed OS 5 Zephyr RTOS Modbus RTU
AI & Deep Learning
PyTorch BiLSTM / CNN / Transformer Audio Feature Engineering On-device Inference
Languages
C / C++ Python Java ARMv7 ASM
03

Contact

Open to
opportunities.

Internships, research collaborations,
or a technical conversation.

location Meknès, Morocco
degree M1 ISOC — UMI
status Available