10 docs tagged with "ai-security"

Crafting inputs that reliably cause model failures - attack techniques, transferability, and robust defense strategies for production AI systems.

Organizational security policies, risk classification frameworks, compliance programs, lifecycle governance, model cards, incident response, and vendor risk management for responsible AI system deployment.

Attacks that corrupt training or fine-tuning data to embed backdoors, trigger unexpected behaviors, or degrade model performance in production.

Taxonomy of jailbreak techniques, why they work, evaluation frameworks, and layered defense strategies for production LLM systems.

Determining whether specific data was used in model training - privacy risks, attack techniques, and defenses for production ML systems.

Querying a model API to reconstruct its weights, replicate its behavior, or steal proprietary training data through systematic probing.

Comprehensive coverage of AI security threats, attack vectors, and defenses for production AI systems.

How prompt injection attacks work, why they are the most critical AI vulnerability in production, and how to defend against them with layered mitigations.

Systematic adversarial testing of AI systems - methodology, automated red teaming, documentation, and building a continuous red team program.

Attack surfaces unique to RAG architectures - document poisoning, retrieval hijacking, indirect prompt injection, embedding collision, cross-tenant leakage, and defense-in-depth strategies for production RAG deployments.