Skip to main content

AI/ML / Gen AI / Threats / DEV

Data Poisoning

CCC.GenAI.TH02

Data poisoning occurs when training, fine-tuning or embedding data is tampered with in order to modify the model's behaviour, for example steering it towards specific outputs, degrading performance or introducing backdoors.

Related Capabilities

IDTitleDescription
CCC.Core.CP02Encryption at Rest Enabled by DefaultThe service automatically encrypts all data using industry-standard cryptographic protocols prior to being written to a storage medium.
CCC.Core.CP06Access ControlThe service automatically enforces user configurations to restrict or allow access to a specific component or a child resource based on factors such as user identities, roles, groups, or attributes.
CCC.GenAI.CP03Embedding Model SelectionAbility to select a foundation model used for tasks like semantic search, clustering, and document similarity by converting text into vector embeddings.
CCC.GenAI.CP06Customizable Model SelectionProvide users the ability to fine-tune models with their own data.
CCC.GenAI.CP21Generate ContentAbility to generate a response given a foundation model, parameter values, and a prompt.
CCC.GenAI.CP22Data ControlEnsures prompts, model outputs, embeddings, and training data fed by customers are not used to train foundation models.
CCC.GenAI.CP24Content ModerationEnsure the service detects and filters abusive, harmful, and sensitive information to ensure responsible and safe use of the service.

Related Controls

IDTitleDescription
CCC.GenAI.CN03Data Provenance and Source VettingEnsure that all data for training, fine-tuning or RAG comes from trusted, approved sources and is authorised for the intended purposes in order to prevent the initial introduction of malicious content or leaked sensitive data.
CCC.GenAI.CN04Sanitisation of Ingested DataValidate and sanitise all data ingested by GenAI systems from extenal sources or internal knowledge bases, whether for training, conversion to vector embeddings, or real-time retireval, in order to remove or redact poisoned or sensitive data before further processing.
CCC.GenAI.CN08Quality Control and Red TeamingEstablish a formal program for quality evaluation and adversarial testing (red teaming) to ensure GenAI system meet all business, quality, security and compliance requirements before getting deployed into production environments.

External Mappings

FrameworkIDRemarks
FINOS-AIGFAIR-SEC-009Data Poisoning
SAIFDPData Poisoning
OWASP-LLM-TOP10LLM04:2025Data and Model Poisoning
MITRE-ATLASAML.T0020Poison Training Data
MITRE-ATLASAML.T0070RAG Poisoning