# AI in the SOC URL: https://justuju.org/concept/ai-in-the-soc/ Layer 9 · Applications & Interfaces Using AI in a security operations centre (to triage alerts, summarise incidents and find vulnerabilities) and the new risks that come with it. ## Simple A security operations centre (SOC) is the team that watches an organisation's systems for attacks. It gets far more alerts than people can read. AI can help: sort alerts, write short summaries of what happened, explain unfamiliar code, and draft the next steps for a person to check. AI tools have also started finding real software bugs before attackers do. But attackers use AI too, to work faster and at larger scale. And an AI that reads logs and emails can itself be fooled by text an attacker planted there. So keep a person in charge of decisions, check the AI's work, and never let it take drastic actions on its own. 1. Alerts: far too many 2. AI sorts: and summarises 3. Analyst checks: evidence first 4. Decision: by a person Like: A fast junior analyst who reads everything overnight and leaves notes on the senior's desk. Where it breaks: A junior learns from mistakes and would notice a note telling them to hide evidence. The AI can be misled by planted text and repeat the same error at scale. ## How it works Triage and summarisation. Models group related alerts, pull context from tickets and threat intelligence, and draft summaries. Their output is a lead, not a verdict: they can invent details, so claims should link to the underlying evidence. Vulnerability discovery. Agents that read code, write test inputs and run them have found real, exploitable bugs, and competition systems have found and patched bugs in open-source code. The SOC's own attack surface. Alerts, logs, emails and tickets contain attacker-controlled text, so a SOC assistant is exposed to prompt injection. Give it read-only access by default, require approval for containment actions, and log its reasoning and tool calls. Adversary use. Threat actors use agents for reconnaissance and exploitation. Defenders should expect faster, wider campaigns and watch for bursts of automated activity. - Automation clears queues but can hide a real alert behind a confident wrong summary. - Read-only assistants are safe but slower; letting AI contain threats saves minutes and risks outages. - Sending logs to a hosted model raises data-handling and residency questions. ## Research Finding bugs. An LLM agent found an exploitable memory-safety bug in widely used database code before it shipped (Project Zero, 2024); in a national competition, autonomous systems found and patched vulnerabilities and were released as open source (AIxCC). Attackers' use. A state-sponsored group used a coding agent to carry out most of an espionage campaign against about 30 targets, a small number of them successfully; the provider says the agent also overstated its results (Anthropic, 2025). Taxonomies. ATLAS catalogues adversary techniques against and with AI, including autonomous attack orchestration (MITRE ATLAS data). Open questions. How to measure whether AI triage lowers missed attacks rather than just time per alert, and how to protect SOC assistants from injection through the very data they analyse. ## Examples as of 2026-11-10 - Microsoft Security Copilot Security Alert Triage Agent in Defender (email alerts generally available; identity and cloud alerts in preview) - Big Sleep vulnerability-finding agent (Google DeepMind and Project Zero) - DARPA AI Cyber Challenge finalist systems (released as open source, 2025) - MITRE ATLAS technique AML.T0124 Autonomous Attack Orchestration ## Sources - From Naptime to Big Sleep: Using Large Language Models To Catch Vulnerabilities In Real-World Code (Google Project Zero): https://projectzero.google/2024/10/from-naptime-to-big-sleep.html - Announcing the Winners of DARPA's AI Cyber Challenge (AIxCC): https://aicyberchallenge.com/ - Disrupting an AI-orchestrated cyber espionage campaign (Anthropic): https://www.anthropic.com/news/disrupting-AI-espionage - MITRE ATLAS data, release 2026.10 (the data behind atlas.mitre.org): https://github.com/mitre-atlas/atlas-data - NIST AI 100-2 E2025: Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations: https://csrc.nist.gov/pubs/ai/100/2/e2025/final - Microsoft Security Copilot Security Alert Triage Agent in Microsoft Defender (Microsoft Learn): https://learn.microsoft.com/en-us/defender-xdr/security-alert-triage-agent --- Justuju · https://justuju.org/ · Content CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote with a link to the page.