AI Red Team Engineering notes, research references, and field notes on AI systems, responsible AI, governance, and compliance.
Global search

Search AI Red Team

Search across the complete knowledge base.

Enter at least two characters to begin.
↑↓ select Enter open Browse the full research archive
NVIDIA AI Red Team · August 4, 2023

Mitigating Stored Prompt Injection Attacks Against LLM Applications

guide Prompt InjectionAgent SecurityAI Red Teaming
Why it matters

NVIDIA explains stored prompt injection in retrieval-augmented applications: an attacker who can influence indexed content can place instructions into data that is later retrieved into another user's model context. Its example shows one poisoned record overriding legitimate evidence, and recommends constraining ingestion, validating provenance, detecting anomalies, and limiting write access.

My takeaway: Treat every retrieved document as untrusted data even after it is parsed or embedded. Restrict who and what can enter the corpus, retain provenance, separate instructions from retrieved content, enforce authorization before retrieval, minimize model and tool privileges, validate consequential outputs, and regression-test targeted and cross-user poisoning rather than relying on prompt sanitization alone.
Keep exploring

More curated notes connected through Prompt Injection and Agent Security.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.