This page shows the most relevant public items for AI Security, ranked by trend activity and review signal. Use weekly for fast changes, monthly for more stable patterns, and all-time for evergreen picks.
Blog • Mar 11, 2026 • OpenAI • Thomas Shadwell, Adrian Spânu
OpenAI frames prompt injection not as simple string-matching but as an evolving social-engineering-like threat that targets tool-using agents. The post defines the problem of malicious external con...
Blog • Feb 23, 2026 • Medium • ZeroDay_Scribe
Hackers have moved beyond stealing passwords; they are now stealing 'Agency.' We explore the terrifying world of Agent Hijacking—where malicious actors redirect an autonomous agent's authority to a...
Paper • Mar 11, 2026 • arXiv • Juhee Kim, Xiaoyuan Liu, Zhun Wang, Shi Qiu, Bo Li, Wenbo Guo, Dawn Song
This comprehensive survey analyzes the emerging security landscape surrounding agentic AI systems capable of autonomous reasoning, tool usage, and multi-step decision-making. The authors categorize...
Blog • Feb 28, 2026 • OpenAI • OpenAI
This post explores security challenges that arise when autonomous AI agents interact with external links and web resources. It discusses how malicious prompts and links could lead to data exfiltrat...
It ranks public content for AI Security using recent discussion, review, and engagement signals so you can triage faster. This guidance is specific to AI Security topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use weekly for fast-moving updates, monthly for stable trend confirmation, and all-time for evergreen references. This guidance is specific to AI Security topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Use the linked entities section to jump to labs, companies, and experts connected to this topic and explore their timelines. This guidance is specific to AI Security topic page on Attendemia and is written so it still makes sense without reading other sections on the page.
Yes. Use the follow button on this page to subscribe and track new high-signal activity. This guidance is specific to AI Security topic page on Attendemia and is written so it still makes sense without reading other sections on the page.