What’s changed in AI security over the past two years

Published

2026-09-08 11:45

Collected

2026-09-11 18:25

---
id: 7574
title: "What’s changed in AI security over the past two years"
source_domain: bugcrowd.com
source_url: "https://www.bugcrowd.com/blog/whats-changed-in-ai-security-over-the-past-two-years/"
published_at: "2026-09-08T11:45:52Z"
tags: ["ai-security", "agentic-ai", "prompt-injection", "bugcrowd", "threat-landscape", "ai-regulation"]
phying_url: "https://phying.com/item/7574"
lang: en
---

# What’s changed in AI security over the past two years

## Summary

Bugcrowd compares its 2024 and 2026 AI security guides: 80% of Fortune 500 run autonomous agents, making memory poisoning and plan hijacking real attack classes — plus regulation and 'AI slop'.

## Intelligence Metadata

- **Sources:** bugcrowd.com
- **Published:** 2026-09-08T11:45:52Z
- **Original:** https://www.bugcrowd.com/blog/whats-changed-in-ai-security-over-the-past-two-years/
- **Phying News:** https://phying.com/item/7574