Tag
#ai-security
5 posts tagged ai-security.
- vulnerability
LLM Security Risks: The Top Threats to Language Models in 2025
Prompt injection, data poisoning, excessive agency, and system prompt leakage — a practitioner breakdown of the LLM security risks catalogued by OWASP and NIST for 2025 deployments.
- threat-intel
Generative AI Risks: A Practitioner's Guide to What Matters
From prompt injection to supply chain poisoning, the generative AI risk landscape is broader than most security teams realize. Here is what the frameworks say and what attackers are doing.
- threat-intel
Machine Learning Security: Key Threats, Attacks, and Defenses
Machine learning security covers adversarial attacks, data poisoning, model theft, and supply chain risks targeting ML systems. Here is what practitioners need to know.
- threat-intel
ChatGPT Security: Key Risks, Vulnerabilities, Enterprise Controls
From DNS-based data exfiltration and command injection in Codex to credential theft and prompt injection, here is what security teams need to know about ChatGPT security in practice.
- deep-dive
AI Agents Are Rewriting the Threat Model: Are Defenders Ready?
Three incidents in three months — Clinejection, the FortiGate campaign, and the OpenClaw exposure wave — show how autonomous AI assistants are collapsing the boundaries security programs were built around.