Skip to content
View poojakira's full-sized avatar
💭
open to work
💭
open to work

Highlights

  • Pro

Block or report poojakira

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
poojakira/README.md

Pooja Kiran — ML Security Engineer

Building security tooling for the ML lifecycle: model supply chain security, LLM red-teaming, adversarial robustness, and privacy-preserving ML.

GitHub · LinkedIn

Projects

Repo What It Does Key Threat Status Evidence
llm-redteam-framework FastAPI scan service: prompt injection, PII leakage, RAG poisoning → SARIF output, PR gate LLM01 Prompt Injection F1=0.70 OOD / 0.93 curated results/scan_metrics.json
hf-model-provenance-scanner Scan HuggingFace models for supply chain attacks; Ed25519 model signing T1683.001 ML Supply Chain 12/12 internal fixture suite tests/redteam/
mcp-security-gateway-monitor MCP tool-call security monitor — layered call inspection and policy decisions T1684, T1687 P99 < 5ms per tool call benchmark/
adversarial-ml-lab FGSM/PGD/C&W attacks on CIFAR-10 ResNet-18; Madry adversarial training AML.T0043 Craft Adversarial Data Literature-consistent results (no weights committed) results/cifar10_resnet18_benchmark.json
model-privacy-attacks Yeom MIA, Fredrikson inversion, DP-SGD defense (synthetic data) T1685 ML Privacy MIA advantage=0.42; ε=0.54 at σ=4.0 results/mia_advantage_report.json
dataset-poisoning-detector Anomaly screening for training data integrity T1685, T1688 Research baseline README.md
PulseNet-RUL-Forecasting Jointly authored RUL forecasting and anomaly-serving research; STRIDE threat model 12 STRIDE surfaces F1=0.54 Isolation Forest, NASA C-MAPSS FD001 docs/evidence/validation_results.json

Security Engineering Focus

  • Threat Modeling: STRIDE across ML pipelines; MITRE ATLAS + ATT&CK v19 mapping
  • Privacy: Membership inference (Yeom 2018), model inversion (Fredrikson 2015), DP-SGD
  • Supply Chain: Ed25519 model signing, SHA-256 artifact manifests, SARIF CI gates
  • LLM Security: OWASP LLM Top 10, RAG poisoning detection, canary token tracking
  • Adversarial ML: FGSM, PGD, C&W attacks; Madry AT on CIFAR-10 ResNet-18

Evidence Policy

All metrics link to committed JSON artifacts in their respective repositories. Synthetic data results are marked as such. Each repo README states what is and is not production-ready. No metric is claimed without a reproducible evidence file.

Pinned Loading

  1. unified-ml-security-platform unified-ml-security-platform Public

    Integration workspace for ML security services with CI, compose validation, scans, and health checks.

    Python

  2. hf-model-provenance-scanner hf-model-provenance-scanner Public

    Scan Hugging Face model repos for provenance, impersonation, pickle-risk, and supply-chain signals.

    Python

  3. llm-redteam-framework llm-redteam-framework Public

    Generate adversarial prompts and evaluate an offline detector for LLM red-team experiments.

    Python

  4. adversarial-ml-lab adversarial-ml-lab Public

    FGSM/PGD/C&W adversarial robustness benchmark harness for CIFAR-10 — maps to MITRE ATLAS AML.T0043

    Python