AI Security Risk

AI security risk refers to vulnerabilities and threats that could compromise the integrity, confidentiality, or availability of AI systems and their outputs. These risks include adversarial attacks, model poisoning, prompt injection, unauthorized access to training data, and supply chain compromises that threaten both the AI system itself and downstream business operations. Understanding and mitigating AI security risks is essential for enterprise governance because security breaches can lead to biased decisions, data theft, regulatory violations, and loss of stakeholder trust in AI-driven processes.

1 item

ResearchGlobal2026-08-10

Kimsuky's Local LLM Operation Breaks the Content-Detection Control Model

South Korean security firm Genians has documented North Korea's Kimsuky threat group running structured local LLM environments to support phishing campaigns, malware development, and analysis of stolen documents. The group is using tools including Ollama, GPT4All, and Msty in what researchers describe as deliberate preparation rather than casual experimentation. For enterprise security and compliance teams, the finding signals that content-based threat detection controls calibrated against pre-AI attack materials are now materially insufficient.

Kimsuky nation-state AI adversarial AI use phishing threat intelligence AI security risk red teaming North Korea