🛡️ AI Security - CWhiting · Scour

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning 🤖Artificial Intelligence

arxiv.org·3d·Hacker News

Sweet Security Launches Agentic AI Red Teaming to Counter ‘Mythos Moment’ 💻Coding Agents

securityweek.com·1d

rl for red teaming: training models to attack and defend themselves 📈Growth Hacking

castform.com·9h·Hacker News

A pragmatic threat model for AI coding agents, with controls you can ship today 📋AGENTS.md

dev.to·23h·DEV

AI security is broken at runtime: Most enterprises don’t realize it yet 🤨AI Criticism

·1d

How are you handling prompt injection across multi-step agent workflows? 🧠Context Engineering

msukhareva.substack.com·6d·Substack

New Claude Mythos becomes the first AI model to clear all cyberattack simulations from Britain's AI safety agency 🤖Anthropic Claude

the-decoder.com

·20h

The Other Half of AI Safety 🛡️AI Safety

personalaisafety.com·1d·Hacker News

The hard core of alignment (is robustifying RL) 🛡️AI Safety

lesswrong.com·6h

The Role of AI Safety Standards in Modern MLOps 🛡️AI Safety

mlops.community·1d

How a Morse Code Message Hacked Grok: Lessons in AI Security for Developers 💉Prompt Injection

dev.to·6d·DEV

I Want to Be a von Neumann Probe: Why We Need to Fix AI Safety 🛡️AI Safety

justinldew.substack.com·2d·Substack

My Agentic Trust Issues: From Prompt Injection to Supply-Chain Compromise on gemini-cli 🐛Bug Bounty

pillar.security·5d·Lobsters

Mythos Preview is the first AI model to complete both of AISI's cyber ranges, which measure models' cyberattack capabilities; GPT-5.5 solved only one of them (A... 🤖AI News

techmeme.com·1d

Hugging Face hosted malicious software masquerading as OpenAI release 🛡️OWASP

artificialintelligence-news.com·2d

How to verify AI-discovered vulnerabilities aren't just training data echoes 🛡️Exploit Mitigations

dev.to·3d·DEV

AI safety tests have a new problem: Models are now faking their own reasoning traces 🤨AI Criticism

the-decoder.com

·6d

Prompt injection through website content: how AI agents can be manipulated by the pages they visit 🤖Web Crawling Politeness

dev.to·6d·DEV

Static Analysis for LLM Prompt Security: A Methodology for Pre-Deploy Vulnerability Detection. 🕳LLM Vulnerabilities

dev.to·4d·DEV

Taming LLMs with NeMo Guardrails 🚧Execution Guardrails

mlops.community·1d

No more posts from CWhiting's subscribed feeds.

Scour all 25695 feeds Learn more about Feeds

Log in to enable infinite scrolling