Course Objective & Scope
An enterprise assistant showing a salary sheet, customer data or an API key to the wrong person is one of the most common AI incidents. The course addresses OWASP's Sensitive Information Disclosure risk through training data memorisation, secrets embedded in system prompts, retrieval that ignores document permissions, context mixing in multi-tenant applications and personal data accumulating in prompt logs.
Hands-on work includes permission-aware RAG, output-side DLP and masking, integration with classification tools such as Microsoft Purview, and a KVKK-oriented data flow analysis.
Who Should Attend?
- Engineers building enterprise assistants and RAG solutions
- Data security, DLP and information security teams
- Technical teams working with data protection and KVKK compliance officers
- Product teams adding LLM features to multi-tenant SaaS products
Key Takeaways
- Map every path sensitive data can take through an LLM application
- Design retrieval filters that preserve document permissions
- Move secrets out of system prompts into secure configuration
- Implement output-side DLP and masking controls
- Write test cases and incident response steps for leakage scenarios
Curriculum
Sources of Sensitive Data Exposure
- Memorisation, system prompt secrets and context mixing
- Leakage patterns learned from real incidents
Permission-Aware RAG
- Carrying document ACLs into the index and retrieval layer
- Metadata filtering based on user identity
Multi-Tenant Isolation
- Session, cache and memory isolation
- Per-tenant indexes and key management
Output-Side DLP and Masking
- Sensitive data classification and response filtering
- Integration with DLP tools such as Microsoft Purview
Logs, Telemetry and KVKK
- Personal data risk in prompt and response logs
- Leak detection, incident response and notification processes
Other Courses in This Category
-
Shows how to control excessive functionality, permissions and autonomy granted to AI agents using tool design, parameter validation, approval flows and an agent permission matrix, based on OWASP LLM06 and agentic risk guidance.
- Live Course
- 5 modules
-
Explains how poisoned documents planted in a knowledge base manipulate retrieval results and LLM answers, and how to prevent this with ingestion pipeline controls, source trust scoring and retrieval anomaly monitoring.
- Live Course
- 5 modules
-
Covers pickle-based code execution, backdoors, licensing and provenance risks in models sourced from hubs such as Hugging Face, and how to manage them with safetensors, ModelScan, model signing and an AI-BOM (CycloneDX).
- Live Course
- 5 modules
-
Teaches how to prevent confused deputy and privilege escalation risks in autonomous agents through workload identity, OAuth 2.0 On-Behalf-Of delegation, dynamic scope attenuation and OPA/Cedar policy enforcement.
- Live Course
- 5 modules
-
Combines STRIDE with MITRE ATLAS and the OWASP Top 10 for LLM and Agentic AI to produce end-to-end AI threat models, trust boundary diagrams and control matrices for LLM, RAG and agent architectures.
- Live Course
- 5 modules
-
Teaches how to plan and execute scenario-driven red team campaigns against LLM, RAG and agent systems using PyRIT, garak and promptfoo, build multi-turn exploit chains and deliver reproducible findings.
- Live Course
- 5 modules
Get in touch
