---
id: 6512
title: "Can AI invent new attack techniques? New research from James Kettle and PortSwigger Research"
source_domain: portswigger.net
source_url: "https://portswigger.net/blog/can-ai-invent-new-attack-techniques-new-research-from-james-kettle-and-portswigger-research"
published_at: "2026-08-12T09:04:45Z"
tags: ["ai-security", "black-hat", "web-security", "http-desync", "portswigger", "autonomous-agents", "attack-research"]
phying_url: "https://phying.com/item/6512"
lang: en
---

# Can AI invent new attack techniques? New research from James Kettle and PortSwigger Research

## Summary

PortSwigger's James Kettle built the HTTP Terminator, an autonomous system generating 30,000 attack vectors and confirming ~700 vulnerable targets, asking whether AI can invent new attack techniques.

## Why it matters

This coverage gives security teams current context for monitoring, validation, and remediation.

## Intelligence Metadata

- **Sources:** portswigger.net
- **Published:** 2026-08-12T09:04:45Z
- **Original:** https://portswigger.net/blog/can-ai-invent-new-attack-techniques-new-research-from-james-kettle-and-portswigger-research
- **Phying News:** https://phying.com/item/6512