Database / Vector

Threats

Version:

ID	Title	Description
CCC.Vector.TH01	Embedding Extraction and Model Inversion	Attackers may infer or reconstruct original data by probing vector similarity APIs, especially with unrestricted access. This enables model inversion attacks, membership inference, and unauthorized data leakage from stored embeddings.
CCC.Vector.TH02	Embedding and Index Poisoning	Adversaries may insert malicious or adversarial vectors into the index through ingestion endpoints, polluting the dataset and degrading search quality, or subtly steering results toward specific outcomes.
CCC.Vector.TH03	Cross-modal or Metadata Leakage	Attackers may infer sensitive information through metadata filters or by correlating embeddings across modalities (e.g., voice and face), bypassing surface-level access controls.
CCC.Vector.TH04	Index Corruption or Downgrade	Attackers with unauthorized access or excessive permissions may tamper with or roll back index versions, potentially restoring poisoned data or breaking downstream integrations.
CCC.Vector.TH05	Embedding Format or Dimension Attacks	Poor validation of embedding formats or dimensions can cause service crashes or logic errors. This can result in denial of service or incorrect similarity results.
CCC.Vector.TH06	Search Result Manipulation via ANN Bias	Approximate nearest neighbor (ANN) algorithms may yield non-deterministic or biased results. Adversaries may exploit these differences to evade detection or bias AI responses.