Perspectives

The controls for managing generative AI risk across prompts, RAG, agents, and outputs, before launch, at runtime, and after deployment.

How security teams turn AI governance into working controls: inventory, risk assessment, red teaming, runtime guardrails, monitoring, and the evidence that proves each one works.

A category map of AI security tools, from discovery and red teaming to runtime guardrails and governance, and how to choose controls for GenAI apps, LLMs, and agents.

The EU has formally sanctioned key players behind Russia’s coordinated disinformation ecosystem. These campaigns, long monitored by ActiveFence, reveal a complex strategy built on narrative laundering, infrastructure resilience, and long-term influence.

GenAI systems introduce a new and rapidly evolving attack surface. This taxonomy outlines the most common GenAI attack vectors; from prompt injection to multimodal evasion; and how enterprises can detect and defend against them.

The AI security risks that appear when models reach production, from prompt injection to model drift, and the controls teams need before launch, at runtime, and after.

As GenAI adoption accelerates, many organizations lack operational safeguards. This article previews Alice’s guide on turning AI safety principles into practical protections through policies, adversarial testing, and red teaming.

How to evaluate AI security software for GenAI apps, models, and agents: the tool categories, lifecycle coverage, and what to ask vendors before you buy.

The ten security risks that appear when generative AI connects to users, data, tools, and workflows, plus the controls that catch each before launch and in production.