Adversarial AI Use

Adversarial AI use refers to deliberate attacks or manipulations targeting AI systems to compromise their performance, security, or decision-making processes. This includes techniques like prompt injection, model poisoning, and adversarial examples designed to exploit vulnerabilities and cause AI systems to produce harmful or incorrect outputs. For enterprise governance, understanding and mitigating adversarial AI risks is critical because successful attacks can undermine AI reliability, create compliance violations, introduce bias into automated decisions, and expose organizations to reputational and legal liability.

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