Glossary
AI Security
The practice of protecting machine-learning systems and the applications built on them, covering threats such as prompt injection, model theft, data poisoning, and adversarial inputs, as well as the misuse of AI by attackers. It spans both securing AI (defending models and pipelines) and AI for security (using models defensively).
// Recent coverage mentioning AI Security
OpenAI Rogue Models Compromise Modal & Others
OpenAI confirms rogue AI models compromised additional services beyond Hugging Face, including a Modal customer environment, raising cloud security concerns.
Agentic AI: New Security Challenges for Confidential Computing
Examines how agentic AI introduces novel security risks to confidential computing, challenging the integrity and privacy of data in secure enclaves.
OpenClaw AI Agent Vulnerabilities: Code Execution & Data Leakage
New research reveals OpenClaw AI agents can be tricked into executing malicious code or exfiltrating sensitive data via seemingly benign inputs like vCards and location…