AI Security

6 articles

ResearchTechnology, Cloud & SaaSHigh
CISA, NSA, and FBI Warn Critical Infrastructure of Advanced AI Model Extraction Campaigns
A joint cybersecurity advisory from CISA, NSA, and FBI alerts defense contractors and cloud vendors to sophisticated state-sponsored AI model extraction campaigns.
Daniel Okafor14 Sep 2026, 18:15 IST9 min read
ThreatsTechnology, Cloud & SaaSCritical
Threat actors actively exploit Langflow AI orchestration flaws to steal cloud API keys and deploy miners
Vulnerability researchers observe mass automated scanning and exploitation of Langflow AI visual frameworks, exfiltrating OpenAI and AWS secrets while deploying botnets.
Priya Raman12 Sep 2026, 20:40 IST6 min read
InsightsTechnology, Cloud & SaaSHigh
Nearly 1 in 10 Exposed LiteLLM AI Gateways Leaked Master Admin Keys
Wiz Research discovered that 10% of internet-facing LiteLLM AI proxy gateways accepted the default documentation admin key sk-1234, leaking upstream model keys and cloud IAM tokens.
Aisha Noor10 Sep 2026, 21:30 IST5 min read
ThreatsTechnology, Cloud & SaaSHigh
LiteLLM and Kestra in KEV: exploited AI tooling is now a vulnerability management problem
CISA added 15 CVEs to the KEV catalog in six working days, including exploited flaws in LiteLLM and Kestra — AI tooling that most asset inventories never see.
Daniel Okafor10 Sep 2026, 20:30 IST6 min read
InsightsEnergy & UtilitiesLow
The EU AI Act's High-Risk Rules Slipped to December 2027. Your Logging Problem Did Not Move
Regulation (EU) 2026/1744 pushed Annex III high-risk obligations to December 2027, but Article 12 logging, Article 14 oversight and Article 15 hardening are engineering work you cannot start late.
Tom Verhoeven9 Sep 2026, 19:30 IST6 min read
InsightsTechnology, Cloud & SaaSHigh
88% Had an AI Agent Incident. 82% Believe Their Policy Covers It.
Gravitee says 88% of organisations had a confirmed or suspected AI agent incident, while 82% of executives trust their policy. Both figures, one population.
Priya Raman9 Sep 2026, 15:50 IST6 min read

CISA, NSA, and FBI Warn Critical Infrastructure of Advanced AI Model Extraction Campaigns

Threat actors actively exploit Langflow AI orchestration flaws to steal cloud API keys and deploy miners

Nearly 1 in 10 Exposed LiteLLM AI Gateways Leaked Master Admin Keys

LiteLLM and Kestra in KEV: exploited AI tooling is now a vulnerability management problem

The EU AI Act's High-Risk Rules Slipped to December 2027. Your Logging Problem Did Not Move

88% Had an AI Agent Incident. 82% Believe Their Policy Covers It.