Skip to content

About

An offline-first computer vision integrity and security assurance platform for auditing datasets, model artifacts, and inference outputs across ML pipelines.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

Β 

History

39 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ›‘οΈ TrustTrace CV

Deep Learning Integrity, Cryptographic Provenance & Adversarial Assurance Toolkit for Computer Vision Pipelines

Python Version PyTorch ONNX Runtime FastAPI SQLite Tests Passing License: MIT


Overview β€’ Key Features β€’ Ecosystem Comparison β€’ System Architecture β€’ Empirical Benchmarks β€’ Quick Start β€’ Python API β€’ CLI Reference β€’ REST API β€’ Documentation


TrustTrace CV Dashboard

The TrustTrace CV interactive dashboard: Real-time mathematical audit traces, cryptographic verification, and offline forensic report generation.



πŸ“– Overview

TrustTrace CV is an offline-first, model-agnostic assurance and cryptographic provenance toolkit designed specifically for safety-critical Computer Vision (CV) pipelines. Modern computer vision systems deployed in autonomous vehicles, robotics, healthcare diagnostics, and automated inspection are increasingly vulnerable to data poisoning, Trojan backdoor insertion, model substitution, and silent inference log manipulation.

Standard MLOps tools focus either on data validation or post-deployment monitoring without verifying cryptographic trust. TrustTrace CV bridges this security gap by delivering zero-trust cryptographic verification, mathematically principled statistical heuristics, and an immutable hash-chained provenance ledgerβ€”operating entirely air-gapped with zero external cloud dependencies.


✨ Key Features

πŸ“ 1. Dataset Integrity & Poisoning Defense

  • Exact Duplicate Flooding (SEC-DS-001): High-throughput cryptographic SHA-256 byte hashing to flag adversarial sample flooding and train/test leakage.
  • Perceptual Near-Duplicate Detection (SEC-DS-001b): 64-bit Difference Hash (dHash) with calibrated Hamming distance filtering to identify recompressed (JPEG quality shift), resized, or subtly filtered duplicates.
  • Label Flipping & BBox Integrity (SEC-DS-002): Optimal bipartite matching via the Hungarian algorithm (Kuhn-Munkres) with class affinity tie-breaking ($IoU \ge 0.50$). Dissected into CLASS_CHANGE, BBOX_MODIFIED, MISSING_ANNOTATION, and ADDITIONAL_ANNOTATION. Guaranteed 0 false positives under annotation reordering.
  • Backdoor Trigger Pattern Detection (SEC-DS-003): Sliding-window Shannon patch entropy analysis ($16 \times 16$ patches) detecting low-entropy synthetic overlays, BadNets triggers, and solid pixel watermarks.
  • Data Poisoning & Distribution Shift (SEC-DS-004): Robust, reference-calibrated Modified Z-scores using Median and Median Absolute Deviation (MAD) across color spaces, resisting heavy outlier masking.
  • Out-of-Distribution (OOD) Detection (SEC-DS-005): Reference-calibrated channel-covariance Mahalanobis Distance identifying semantic domain anomalies and corruptions.
  • Structural Schema Validation: Offline parsers for YOLO (v5/v8) text coordinates and COCO 1.0 JSON schemas.

🧠 2. Model Integrity & Checkpoint Security

  • Cryptographic Manifest Hashing: SHA-256 digest calculation for model weights, architectures, and associated assets.
  • Dual-Scheme Signature Verification:
    • Symmetric HMAC-SHA256: High-speed, local tamper detection with timing-attack safe comparisons (hmac.compare_digest).
    • Asymmetric RSA-2048 PKCS#1v15: Enterprise-grade public-key attestation using X.509 PEM certificates.
  • Safe Deserialization (weights_only=True): Strict PyTorch unpickling protection preventing arbitrary code execution and Zip Slip exploits from untrusted checkpoint files.
  • Multi-Format Support: Native structural introspection for PyTorch (.pt, .pth), TorchScript bytecode (.ts), and ONNX graphs (.onnx).
  • Model Substitution Protection: Deterministic parameter count and tensor structure verification preventing unauthorized model swaps.

⛓️ 3. Tamper-Evident Inference Provenance Ledger

  • Append-Only Cryptographic Chain: Every logged inference record is cryptographically linked to the previous record (previous_record_hash $\to$ current HMAC), forming an immutable hash chain.
  • Strict Monotonic Sequencing: Enforces gapless, strictly increasing sequence_number counters to instantly detect dropped, injected, or reordered frames.
  • Anti-Replay Nonce Verification: Cryptographic UUID nonces prevent replay attacks from recorded telemetry streams.
  • Canonical JSON Serialization: Deterministic key sorting (sort_keys=True) and compact whitespace elimination (separators=(',', ':')) preventing byte-level hashing ambiguities.

πŸ“Š 4. Full-Stack Assurance & Forensic Reporting

  • Interactive Forensic Reports: Generates self-contained, offline HTML audit reports with base64-embedded anomaly visualizations and complete audit logs.
  • Live REST API & Dashboard: Asynchronous FastAPI service paired with a lightweight web UI providing real-time mathematical audit traces.
  • Zero-Trust Adapter Architecture: Modular adapters for Cleanlab, CleanVision, IBM ART, BackdoorBench, TrojAI, in-toto, and Cosign that degrade honestly to NOT_ASSESSED in offline air-gapped environments without generating simulated passes.

βš–οΈ How It Compares

Capability TrustTrace CV Deepchecks (Vision) CleanVision IBM ART Sigstore / Cosign
Primary Scope End-to-End Cryptographic & Statistical Assurance ML Validation & Testing Visual Data Quality Adversarial Attacks & Robustness Container / Artifact Signing
Cryptographic Provenance βœ… Native (HMAC + RSA hash chaining) ❌ None ❌ None ❌ None βœ… Signature only
Hungarian BBox & Label Audit βœ… Optimal Bipartite Matching ⚠️ Generic Heuristics ❌ None ⚠️ Indirect ❌ None
Patch-Level Entropy Scans βœ… Native ($16 \times 16$ Shannon Entropy) ❌ None ❌ None ⚠️ Complex Defense ❌ None
Perceptual Near-Duplicates βœ… 64-bit dHash (Hamming Dist $\le 8$) ⚠️ Basic Duplicates βœ… Visual Near-Dup ❌ None ❌ None
Monotonic Inference Ledger βœ… Gapless Sequence + Anti-Replay ❌ None ❌ None ❌ None ❌ None
Air-Gapped / Offline Native βœ… 100% Offline (No Cloud Calls) ⚠️ Requires Dependencies βœ… Offline βœ… Offline ⚠️ Needs Rekor/Fulcio
Safe Deserialization βœ… Enforced (weights_only=True) ⚠️ Standard Pickling ❌ N/A ⚠️ Standard Loading ❌ N/A
Self-Contained Offline Reports βœ… Interactive HTML (Base64 embed) ⚠️ HTML / Cloud ❌ None ❌ None ❌ None

πŸ—οΈ System Architecture

TrustTrace CV enforces an end-to-end pipeline verifying assets at every phase of the vision lifecycle:

flowchart TD
    subgraph INGESTION["1. Ingestion Layer"]
        A1["Raw CV Dataset (YOLO / COCO)"]
        A2["Model Artifact (.pt / .ts / .onnx)"]
        A3["Inference Stream (.jsonl)"]
    end

    subgraph ENGINE["2. TrustTrace Core Assurance Engine"]
        B1["Dataset Inspector & Schema Parser"]
        B2["Security Heuristics Suite"]
        B3["Safe Model Loader (weights_only=True)"]
        B4["Cryptographic Verifier (HMAC / RSA)"]
        B5["Inference Provenance Validator"]

        B1 --> B2
        B3 --> B4
    end

    subgraph CHECKS["3. Mathematical Verification Battery"]
        C1["Exact SHA-256 + Perceptual dHash"]
        C2["Hungarian IoU Bipartite Matcher"]
        C3["Sliding Shannon Patch Entropy"]
        C4["Reference-Calibrated Robust MAD"]
        C5["Channel Mahalanobis Distance"]
        C6["Hash Chaining & Sequence Monotonicity"]
        
        B2 --> C1
        B2 --> C2
        B2 --> C3
        B2 --> C4
        B2 --> C5
        B5 --> C6
    end

    subgraph AUDIT["4. Tamper-Evident Storage & Reporting"]
        D1[("SQLite Audit Event Store (Append-Only)")]
        D2["Evidence Correlator & Verdict Engine"]
        D3["Self-Contained Offline HTML Report"]
        D4["Structured JSON Audit Log"]

        C1 & C2 & C3 & C4 & C5 & C6 & B4 --> D1
        D1 --> D2
        D2 --> D3
        D2 --> D4
    end
Loading

πŸ”¬ Empirical Benchmarks & Scientific Validation

TrustTrace CV enforces zero experimental leakage: thresholds are selected strictly on a dedicated Calibration Split and evaluated on an independent Evaluation Benchmark Split (130 evaluation samples, 30 reference baselines).

The table below reflects empirical results measured directly from our reproducible test harness (scripts/run_benchmark.py):

Detector / Assurance Module Threat Model Evaluated Latency (ms) Peak Memory Precision Recall F1 Score AUROC AUPR FPR
Exact Duplicate (SHA-256) Adversarial Dataset Flooding 1.13 ms 13.5 KB 0.500 1.000 0.667 β€” β€” 0.111
Perceptual dHash (Hamming $\le 8$) Recompression / Resizing Evasion 367.43 ms 127.5 KB 0.563 0.900 0.692 0.742 0.578 0.467
Hungarian IoU Matching Label Flipping & BBox Alterations 59.84 ms 26.7 KB 1.000 1.000 1.000 β€” β€” 0.000
Sliding Shannon Patch Entropy BadNets Solid Trigger Overlays 938.31 ms 318.7 KB 1.000 0.400 0.571 0.870 0.864 0.000
Ref-Calibrated Robust MAD Feature Poisoning & Color Shift 26.90 ms 74.6 KB 0.714 1.000 0.833 0.987 0.977 0.267
Ref-Calibrated Mahalanobis Out-of-Distribution (OOD) Samples 19.66 ms 23.2 KB 0.692 0.600 0.643 0.796 0.783 0.133

Note

  • Zero False Positives on Label Permutations: The Hungarian bipartite matcher achieves an F1-score of 1.000 with 0 false positives when clean annotations are merely reordered.
  • Robust Outlier Resistance: Reference-calibrated MAD achieves 0.987 AUROC, substantially outperforming uncalibrated global Z-scores that suffer from variance inflation when poisoned samples exceed 10% of the dataset.

🚦 Assurance Verdict Framework

Every subsystem check, API endpoint, and aggregated forensic report produces an explicit, unambiguous verdict:

                  β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                  β”‚ Are findings empty or missing? β”‚
                  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                 β”‚
                     Yes ────────┴──────── No
                      β”‚                    β”‚
              [INCONCLUSIVE]      β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                                  β”‚ Cryptographic mismatch  β”‚
                                  β”‚ or tamper detected?     β”‚
                                  β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                              β”‚
                                  Yes ────────┴──────── No
                                   β”‚                    β”‚
                                [FAIL]         β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
                                               β”‚ Any anomalies   β”‚
                                               β”‚ or shifts found?β”‚
                                               β””β”€β”€β”€β”€β”€β”€β”€β”€β”¬β”€β”€β”€β”€β”€β”€β”€β”€β”˜
                                                        β”‚
                                            Yes ────────┴──────── No
                                             β”‚                    β”‚
                                   [ANOMALIES_DETECTED]        [PASS]
  • PASS: All required cryptographic and statistical assurance checks executed with zero detected anomalies.
  • ANOMALIES_DETECTED: Statistically significant deviations detected (e.g. perceptual duplicates, label discrepancies, trigger patterns, OOD outliers).
  • FAIL: Definite security compromise (signature mismatch, broken hash chain, sequence gap, payload tampering).
  • INCONCLUSIVE: Findings are empty or evidence is insufficient. Empty results never default to PASS.
  • NOT_ASSESSED: A check could not execute because an optional dependency or reference baseline was not provided.

πŸš€ Quick Start Guide

Prerequisites

  • Operating System: Linux, macOS, or Windows
  • Python: 3.10, 3.11, or 3.12
  • Hardware: CPU standard; GPU optional for downstream model inference

1. Installation

Clone the repository and install dependencies in an isolated virtual environment:

# Clone repository
git clone https://github.com/x2ankit/trusttracecv.git
cd trusttracecv

# Create and activate conda or venv environment
conda create -n trusttrace python=3.12 -y
conda activate trusttrace

# Install core dependencies
pip install -r requirements.txt

2. Configure Cryptographic Environment

TrustTrace CV enforces zero hardcoded secrets. Copy the environment template and set secure keys:

cp .env.example .env

Edit .env to supply high-entropy secrets for cryptographic signing:

# Cryptographic Keys (Required for HMAC operations)
TRUSTTRACE_CV_HMAC_SECRET="replace_with_a_secure_random_hmac_key_for_inference"
TRUSTTRACE_CV_MANIFEST_SECRET="replace_with_a_secure_random_manifest_hmac_key"

# Optional: Path to RSA keys for asymmetric manifest signing and verification
TRUSTTRACE_PRIVATE_KEY_PATH="./private_key.pem"
TRUSTTRACE_PUBLIC_KEY_PATH="./public_key.pem"

To generate a standard RSA-2048 keypair:

openssl genrsa -out private_key.pem 2048
openssl rsa -in private_key.pem -pubout -out public_key.pem

3. Generate Synthetic Fixtures & Verify Setup

Generate reproducible offline test datasets and run the full test suite:

# Generate synthetic dataset and model fixtures
python scripts/generate_fixtures.py

# Run all 155 automated unit & integration tests
pytest tests/ -v

4. Launch the Server & Web Dashboard

Start the FastAPI backend with the interactive UI:

python run_server.py

Open your browser at http://localhost:8001 (or http://localhost:8000) to inspect datasets, audit models, and review live cryptographic event logs.


πŸ’» Python API Examples

1. Auditing a Computer Vision Dataset

from pathlib import Path
from src.dataset.inspector import inspect_yolo_dataset
from src.dataset.security_checks import (
    check_duplicate_flooding,
    check_label_flipping,
    check_trigger_patterns,
    check_data_poisoning,
)

dataset_path = Path("data/fixtures/clean")
ref_annotations = Path("data/fixtures/clean/annotations_reference.json")

# 1. Parse YOLO dataset
dataset_summary = inspect_yolo_dataset(dataset_path)

# 2. Execute statistical heuristics
findings = []
findings.extend(check_duplicate_flooding(dataset_path))
findings.extend(check_trigger_patterns(dataset_path))
findings.extend(check_data_poisoning(dataset_path))
findings.extend(check_label_flipping(dataset_path, reference_annotations_path=ref_annotations))

print(f"Dataset audited: {dataset_summary.total_images} images. Findings: {len(findings)}")

2. Cryptographic Model Manifest & Verification

from pathlib import Path
from src.models.integrity import inspect_model, create_manifest, verify_manifest_signature

model_path = Path("models/fixtures/dummy_detector.pt")
manifest_path = Path("models/fixtures/manifest.json")

# 1. Create a signed manifest
manifest = create_manifest(
    model_dir=model_path.parent,
    output_path=manifest_path,
    private_key_path=Path("private_key.pem")
)

# 2. Inspect model format safely (weights_only=True)
inspection = inspect_model(model_path, manifest_path=manifest_path)
print(f"Model: {model_path.name} | Status: {inspection.status} | SHA-256: {inspection.sha256[:16]}...")

3. Recording and Verifying Inference Provenance

from src.inference.provenance import record_inference_event
from src.inference.verifier import verify_inference_chain

# 1. Log an inference event with HMAC cryptographic sealing
record = record_inference_event(
    image_id="frame_0001.png",
    model_id="yolov8n-coco",
    prediction={"classes": ["pedestrian"], "confidences": [0.94], "boxes": [[10, 20, 50, 80]]},
    execution_time_ms=14.2,
    secret_key="my_secret_signing_key"
)

# 2. Verify provenance integrity across the log
verification_findings = verify_inference_chain(
    log_path=Path("audit_events.sqlite"),
    secret_key="my_secret_signing_key"
)

⌨️ Command-Line Interface (CLI)

TrustTrace CV provides a rich, colorized CLI powered by Typer and Rich:

# Audit a YOLO or COCO dataset
python -m src.cli audit-dataset --dataset-dir data/fixtures/clean --format yolo

# Audit a model checkpoint against a reference manifest
python -m src.cli audit-model --model-path models/fixtures/dummy_detector.pt --manifest-path models/fixtures/manifest.json

# Verify an inference provenance log
python -m src.cli audit-inference --log-path data/fixtures/inference.jsonl

# Run the complete end-to-end pipeline and export a forensic report
python -m src.cli audit-all --dataset-dir data/fixtures/clean --model-path models/fixtures/dummy_detector.pt --output-dir reports/

πŸ”Œ REST API Reference

Method Endpoint Description Request Payload / Params
GET /api/health Service health status check None
POST /api/upload/dataset Upload ZIP dataset (YOLO/COCO) with Zip-Slip defense multipart/form-data (file, format)
POST /api/audit/dataset Trigger asynchronous dataset security audit {"dataset_path": "...", "format": "yolo"}
POST /api/audit/model Trigger model structural & cryptographic audit {"model_path": "...", "manifest_path": "..."}
POST /api/inference/log Log an inference prediction with HMAC provenance {"image_id": "...", "model_id": "...", "prediction": {...}}
GET /api/audit/status Polling endpoint for active background audits None
GET /api/audit/events/{id} Chronological audit trail from SQLite ledger Path parameter id (sanitized alphanumeric)
GET /api/audit/records/{id} Detailed image-level anomaly records Path parameter id
GET /api/reports/html/{id} Download self-contained offline HTML forensic report Path parameter id
GET /api/reports List all historical JSON audit reports None

πŸ“‚ Project Structure

trusttracecv/
β”œβ”€β”€ assets/                     # Architectural diagrams, dashboard previews
β”‚   β”œβ”€β”€ ui.png
β”‚   └── ui_screenshot.jpg
β”œβ”€β”€ data/                       # Dataset directories (ignored by git)
β”‚   β”œβ”€β”€ benchmark/              # Calibration & evaluation splits
β”‚   └── fixtures/               # Synthetic YOLO/COCO testing fixtures
β”œβ”€β”€ docs/                       # Technical specifications & guides
β”‚   β”œβ”€β”€ API_REFERENCE.md        # Comprehensive REST API specifications
β”‚   β”œβ”€β”€ ARCHITECTURE.md         # Subsystem dataflows & architectural design
β”‚   β”œβ”€β”€ DATASET_TESTING.md      # Mathematical formulations & benchmark protocols
β”‚   β”œβ”€β”€ DEVELOPMENT.md          # Developer setup & contribution guidelines
β”‚   └── SECURITY_AND_THREAT_MODEL.md # Threat models, cryptanalysis & boundaries
β”œβ”€β”€ models/                     # Model weights & manifests (ignored by git)
β”‚   └── fixtures/               # Synthetic PyTorch/TorchScript test models
β”œβ”€β”€ reports/                    # Generated forensic JSON & HTML audit outputs
β”‚   └── benchmark_results.json  # Empirical benchmark results
β”œβ”€β”€ scripts/                    # Generation and benchmark utilities
β”‚   β”œβ”€β”€ generate_fixtures.py    # Synthetic fixture generator
β”‚   β”œβ”€β”€ generate_benchmark.py   # Benchmark split generator
β”‚   β”œβ”€β”€ run_benchmark.py        # Scientific benchmark runner
β”‚   └── demo_behavior.py        # End-to-end behavioral fingerprinting demo
β”œβ”€β”€ src/                        # Core TrustTrace CV library
β”‚   β”œβ”€β”€ api/                    # FastAPI backend & SQLite audit DB
β”‚   β”‚   β”œβ”€β”€ app.py
β”‚   β”‚   └── audit_db.py
β”‚   β”œβ”€β”€ dataset/                # Dataset inspection & statistical security checks
β”‚   β”‚   β”œβ”€β”€ inspector.py
β”‚   β”‚   └── security_checks.py
β”‚   β”œβ”€β”€ evidence/               # Evidence correlation & verdict calculation
β”‚   β”‚   └── correlator.py
β”‚   β”œβ”€β”€ inference/              # Inference HMAC provenance & replay verifier
β”‚   β”‚   β”œβ”€β”€ provenance.py
β”‚   β”‚   └── verifier.py
β”‚   β”œβ”€β”€ integrations/           # Zero-trust adapters (Cleanlab, ART, in-toto, etc.)
β”‚   β”œβ”€β”€ models/                 # Model integrity, manifests & runtime probes
β”‚   β”‚   β”œβ”€β”€ behavioral_fingerprint.py
β”‚   β”‚   β”œβ”€β”€ controlled_transformations.py
β”‚   β”‚   β”œβ”€β”€ integrity.py
β”‚   β”‚   β”œβ”€β”€ runtime.py
β”‚   β”‚   └── trigger_probe.py
β”‚   β”œβ”€β”€ reporting/              # HTML & JSON report generators
β”‚   β”‚   β”œβ”€β”€ html_generator.py
β”‚   β”‚   └── report_generator.py
β”‚   β”œβ”€β”€ shift/                  # Distribution shift detection
β”‚   β”‚   └── distribution.py
β”‚   └── ui/                     # Lightweight frontend dashboard
β”‚       β”œβ”€β”€ index.html
β”‚       β”œβ”€β”€ app.js
β”‚       └── style.css
β”œβ”€β”€ tests/                      # Automated test suite (155 pytest cases)
β”‚   β”œβ”€β”€ conftest.py
β”‚   β”œβ”€β”€ test_api.py
β”‚   β”œβ”€β”€ test_audit_security_fixes.py
β”‚   β”œβ”€β”€ test_behavior.py
β”‚   β”œβ”€β”€ test_dataset.py
β”‚   β”œβ”€β”€ test_dataset_benchmarking.py
β”‚   β”œβ”€β”€ test_inference.py
β”‚   β”œβ”€β”€ test_models.py
β”‚   └── test_report.py
β”œβ”€β”€ .env.example                # Template for cryptographic secrets
β”œβ”€β”€ .gitignore                  # Git ignore rules
β”œβ”€β”€ LICENSE                     # MIT License
β”œβ”€β”€ pytest.ini                  # Pytest configuration
β”œβ”€β”€ requirements.txt            # Python dependencies
└── run_server.py               # Server entry point

πŸ”’ Threat Model & Security Boundaries

TrustTrace CV addresses specific adversarial threats across the ML pipeline:

Subsystem Defended Threats Out of Scope / Explicit Limitations
Dataset Assurance Exact sample flooding, recompressed near-duplicates, label flipping, bounding-box shifts, synthetic solid triggers (BadNets), color distribution poisoning, semantic domain outliers. Invisible adversarial perturbations with zero pixel-level statistical signature ($L_\infty \le 1/255$).
Model Security Checkpoint tampering, model substitution, unauthorized fine-tuning, malicious pickle deserialization exploits. Dynamic runtime memory tampering within secure hardware enclaves.
Inference Provenance Prediction tampering, frame dropping, record reordering, telemetry replay attacks. Physical camera sensor spoofing prior to digitized frame ingestion.
Storage & API Path traversal (Zip Slip), database tampering, unsigned audit records, timing attacks. Physical write-once hardware storage (WORM) enforcement.

πŸ§ͺ Testing & Quality Assurance

TrustTrace CV enforces test-driven quality assurance. The entire suite runs 100% offline using synthetic mathematical fixtures:

# Execute the full pytest suite
pytest tests/ -v

# Run with test coverage report
pytest --cov=src tests/
================================ test session starts =================================
platform win32 -- Python 3.12.14, pytest-8.3.3
rootdir: trusttracecv
collected 155 items

tests/test_api.py .........................                                    [ 16%]
tests/test_audit_security_fixes.py ........................................... [ 44%]
tests/test_behavior.py ........                                                [ 49%]
tests/test_dataset.py .......................                                  [ 64%]
tests/test_dataset_benchmarking.py ....................                        [ 77%]
tests/test_inference.py .................                                      [ 88%]
tests/test_models.py .................                                         [ 99%]
tests/test_report.py .                                                         [100%]

================================= 155 passed in 20.30s ================================

πŸ“š Documentation Index

For complete architectural specifications, threat analyses, and development guides:


πŸ“„ License & Citation

TrustTrace CV is released under the MIT License.

@software{trusttracecv2026,
  author = {Ankit Tripathy and Contributors},
  title = {TrustTrace CV: Deep Learning Integrity, Cryptographic Provenance & Adversarial Assurance Toolkit for Computer Vision Pipelines},
  year = {2026},
  publisher = {GitHub},
  url = {https://github.com/x2ankit/trusttracecv}
}
Engineered for Zero-Trust, Air-Gapped Computer Vision Assurance.

About

An offline-first computer vision integrity and security assurance platform for auditing datasets, model artifacts, and inference outputs across ML pipelines.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Contributors

Languages