Models and training data
5 guides tagged Models and training data, grouped by topic, with the SDLC phase and role each is written for.
Runtime, cloud & APIs
1 guideAI security
4 guidesTreat model releases as executable supply-chain inputs
Verify provenance, constrain loading and preserve the relationship between model weights, configuration and runtime dependencies.
Development, Release · Developers, AppSec engineers, Platform engineers and SREs
Protect training and retrieval data from targeted poisoning
Track who can influence datasets, keep evaluation independent and investigate targeted behavior changes without relying on aggregate accuracy.
Development, Testing, Release, Security program · Developers, AppSec engineers, Platform engineers and SREs
Assess extraction, membership and inference risks
Define what an adversary can observe and measure privacy leakage without confusing a model’s output with proof about its training data.
Design, Development, Release · AppSec engineers
Defend agent memory and context against poisoning (OWASP ASI06)
OWASP ASI06 Memory & Context Poisoning: how an instruction or false fact saved once in agent memory, conversation summaries or a retrieval store steers later sessions, users and agents, and the write, scope, provenance, expiry and recovery controls that contain it.
Design, Development · Developers, AppSec engineers