Ogulcan Aydogan

LLM Cost Guardian Ogulcan Aydogan (10 projects)

Transparent proxy for multi-provider LLM cost tracking, budgeting, and optimization. Supports OpenAI, Anthropic, Azure, Bedrock, and Vertex AI with real-time cost headers.

Verifiable AI Output Ledger Ogulcan Aydogan (10 projects)

Cryptographic ledger for AI output verification using Merkle trees and digital signatures. Tracks, timestamps, and proves the authenticity of AI-generated content with tamper-evident audit trails.

LLM Supply Chain Attestation Ogulcan Aydogan (10 projects)

Supply chain security for LLM artifacts using Sigstore, in-toto, and SLSA frameworks. Generates signed attestations for model weights, training data, and inference outputs.

Prompt Injection Firewall Ogulcan Aydogan (10 projects)

Runtime firewall that detects and blocks prompt injection attacks against LLM applications. Covers OWASP LLM Top 10 attack vectors with configurable detection rules.

Sovereign RAG Gateway Ogulcan Aydogan (10 projects)

Policy-first retrieval-augmented generation gateway with PHI/PII redaction, access control, and audit logging. Self-hostable with no mandatory cloud dependencies.

AI Provenance Tracker Ogulcan Aydogan (10 projects)

Multi-modal AI content detection and C2PA provenance verification across text, images, audio, and video. Explainable confidence scoring with signal-by-signal breakdown.

LLM SLO eBPF Toolkit Ogulcan Aydogan (10 projects)

Kubernetes-native observability tool using eBPF to capture kernel signals and correlate them with OpenTelemetry traces for LLM SLO attribution.

AI Model Card Generator Ogulcan Aydogan (10 projects)

CLI pipeline that pulls model metadata from HuggingFace, W&B, and MLflow, runs fairness analysis, checks EU AI Act compliance, and exports model cards.

MMSAFE-Bench Ogulcan Aydogan (10 projects)

Multi-modal safety evaluation benchmark for AI systems. Covers 20 hazard categories and 9 attack strategies aligned with MLCommons AI Safety standards.

AI Regulation Compliance Scanner Ogulcan Aydogan (10 projects)

Rule-driven scanner that checks AI systems against EU AI Act, UK AI regulations, and NIST AI RMF requirements. Deterministic pass/warn/fail scoring.