Mamun Akand

Mamun Akand — Portfolio

Security Research Engineer · Applied Cryptography & AI Security

I design and harden secure systems across cryptography, DLP, and AI/agentic workflows. Recent wins: O(N)→O(1) multi‑recipient encryption, 60%+ key size reduction, and 96.4% location verification accuracy.

Download Resume Email LinkedIn GitHub
Encryption
Encryption cost O(N)→O(1), 60%+ smaller keys
AI Security
Model Extraction, inversion, poisoning, prompt injection
DLP
Forensic watermarking + tamper‑evident metadata
Location Verification
96.4% verification accuracy

Core focus areas

Applied Cryptography Privacy Enhancing Technologies Weighted Secret Sharing Proof-of-Location Local AI Model Security DLP & Watermarking Agentic System Security Credential Privacy & Security

Currently at Huawei (Security R&D). Ph.D. Computer Science (University of Calgary; published in IEEE/ACM venues).

Learning Highlights

Actively building skills aligned with security & AI. See all

25%
AWS Solutions Architect – Associate
Cloud · ETA 2025-10-31

Selected Security Projects

A few highlights. See all projects

Scalable Multi‑Recipient Encryption

Problem: Confidential file sharing cost scales linearly with recipients (O(N)).
Action: Designed scheme with pairing‑based cryptography; optimized keying.
Result: Reduced encryptions from O(N)→O(1) and cut key size by 60%+.

C++ MCL (pairings) Linux Valgrind GoogleTest

Risk‑Weighted Secret Sharing

Problem: Uniform shares enabled insider collusion risk.
Action: Introduced dynamic, risk‑based weights (MCDM) with threat modeling.
Result: Lowered collusion risk; preserved O(1) reconstruction; integrated into product line.

C++ OpenSSL MCDM‑AHP Linux

DLP: Forensic Watermarking & Tamper‑Evident Metadata

Problem: Insider leak investigations were slow and storage‑heavy.
Action: Built robust watermarking and metadata chaining; production‑integrated.
Result: Faster investigations and reduced storage footprint.

C++ OpenSSL Docker Linux

Privacy‑Preserving AI Proxy (PPAP)

PII‑aware proxy for safer AI inference.

Action: Reverse proxy that strips PII before routing to on‑prem/cloud LLMs; combined deterministic redaction and context‑aware masking.
Result: Reduced data leakage risk; containerized for self‑service deployment.

FastAPI Python Microsoft Presidio spaCy TinyLlama Mistral Docker

View Repository

AI Research Assistant Pipeline

Action: Auto‑extracts technologies and gaps; generates reports; optimized for conference research.
Result: Cut manual analysis time by 50%+.

Python LangChain LangGraph Ollama Docker

Publications

Selected venues: IEEE TDSC, ACM CCS, ACNS, ACISP, IEEE Access. See full list:

View Publications

Core Skills

Programming

C++Java (Android)PythonBash

Cryptography

OpenSSLPairings (MCL)ZK ProofsIBM Idemix

AI/LLM

LangChainLangGraphOllamaTinyLlamaMistralPresidio

Secure Systems

Attribute‑Based EncryptionWeighted Secret SharingTEEThreat ModelingDLP

DevOps & Testing

DockerGitValgrindGoogleTest

Documentation

LaTeXConfluenceMarkdown

Contact

Waterloo, ON · mamun@mamunakand.ca · +1-403-499-9267

Download Resume LinkedIn