Dhergam LABIB

• Prepared approximately 10 bug bounty / responsible disclosure reports with technical impact, root cause,
reproducible steps, evidence, and fixes.
• Focused on code-driven research, web/API security, authorization logic, server-side failure handling, Git transport
risk, and containment weaknesses.
• Built local PoCs and evidence packages for programs and open-source targets including Google and Vercel
ecosystem research.
Network setup, PC configuration, dashboards, database-backed systems and practical automation
• Configured PCs, software, networking, cabling, workstation environments, and troubleshooting workflows for real
world freelance setups.
• Developed practical business systems and dashboards using web/mobile technologies, SQL databases, APIs,
spreadsheets and deployment workflows.
• Delivered technical documentation, handover notes, and organized operational data flows for maintainable day-to
day use.

4,
• Built an edge-ready IDS/IPS product combining high-performance packet capture, deep packet inspection, ML
inference, PCAP rotation, memory guard, and live visualization.
• Personally trained, tuned, evaluated, converted, and integrated six ONNX models into the detection pipeline instead
of relying on prebuilt models.
• Implemented 74 flow-level features aligned with the trained ML pipeline for binary attack detection and multiclass
attack classification.
• Designed inspection coverage across Ethernet/IP/TCP/UDP plus DNS, HTTP, TLS, SSH, MQTT and protocol
heuristics for suspicious traffic.
• Optimized for Raspberry Pi 4 constraints with RAM limits, flow caps, ARM64 build/deployment workflow, and
dashboard access on port 8080. systems, code generation, automation, evaluation and technical research
• Built and used AI-assisted workflows for research, software planning, code review, debugging, documentation, and
security report preparation.
• Worked with AI agents and multi-step agent-style workflows for breaking technical tasks into planning, execution,
verification and refinement stages.
• Applied AI experience to model training, feature engineering, dataset preparation, testing outputs, prompt design,
and practical engineering decisions.