AI Security
Attacking AI systems, and defending them.
AI security covers the ways AI systems get attacked — prompt injection, data poisoning, jailbreaks, model extraction — and the defenses against them, from guardrails and red teaming to keeping autonomous agents inside safe bounds.
2 episodes
- The First Fully Autonomous AI Attack Is 18 Months Away | Kristin Lovejoy
- Vercel's Playbook for AI Agents: From Vibe Check to Production | Malte Ubl
Explainers on this topic
Terms on this topic
- AI Guardrails
- AI Red Teaming
- Backdoor Attack
- Data Poisoning
- Evasion Attack
- Excessive Agency
- Jailbreaking
- Membership Inference Attack
- Model Denial of Service
- Model Inversion Attack
- Prompt Injection
- Token Leakage