Analysis · curated 21 Jul 2026
CyberTalks: Data Poisoning Attacks on ML & Agentic AI Systems | Jason Ross |COASP - YouTube
First reported · updated · 3 reports youtube.com
Coverage timeline
Why it matters
AI data poisoning lets attackers alter model behavior without touching code, and RAG/vector-store poisoning is an increasingly active attack surface that defenders must address with provenance and monitoring.
An explainer on AI data poisoning describes how attackers corrupt the data a model learns from, fine-tunes on, or retrieves — including training data, alignment data, and RAG knowledge bases — so a poisoned model behaves as the attacker intends while passing ordinary validation. It distinguishes data poisoning from prompt injection, jailbreaking, evasion, and model poisoning, and notes research (e.g. Carlini et al.'s web-scale poisoning work) showing under 1% poisoned data can measurably change behavior, recommending provenance, access control, monitoring, and rollback as layered defenses.