🔐 AI Security - zihaozhu.ai · Scour

Adversarial AI: Understanding the Threats to Modern AI Systems 🛡️AI Safety

blog.jetbrains.com·2d

Why LLMs Hallucinate Vulnerabilities Part Two: Evolution of AI Red Teaming 🛡️AI Safety

medium.com·5d

Unpacking AI security in 2026 from experimentation to the agentic era 🤖AI Agents

theregister.com·2h

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense 🛠️Prompt Engineering

arxiv.org·6h

Journey into AI Security: Learning AI from Scratch ⚖️Trustworthy AI

medium.com·1d

Prompt Injection: The Silent Failure Mode of Enterprise AI Security 💉Prompt Injection

princetonits.com·19h

Intro to AI Security and Threat Modelling 101 🛡️AI Safety

medium.com·4d

0DIN is open-sourcing AI security and the hard-earned knowledge behind it ⚖️Trustworthy AI

blog.mozilla.org·17h

RedSOC: Open-source framework to benchmark adversarial attacks on AI-powered SOCs — 100% detection rate across 15 attack scenarios [paper + code] 📄AI Research

github.com·1d·DEV

Apiiro CLI turns AI coding assistants into full-stack security engineers 🛠️Prompt Engineering

helpnetsecurity.com·2h

ETSI EN 304 223 Securing Artificial Intelligence (SAI); Baseline Cyber Security Requirements for AI Models and Systems 🛡️AI Safety

etsi.org·23h

Prompt Injection Isn’t the Problem. This Is. ⚖️Trustworthy AI

medium.com·1d

I Bypassed an AI Paywall in 5 Minutes. Here's What That Tells Us About AI Security in 2026. 🛡️AI Safety

medium.com·4d

On-device Apple Intelligence vulnerable to prompt injection techniques 💉Prompt Injection

appleinsider.com·21h

Tracking the new vendors in AI Security ⚖️Trustworthy AI

stiennon.substack.com·1d·Substack

Y2K 2.0: The AI security reckoning 🛡️AI Safety

anildash.com·10h

Have we already lost? Part 2: Reasons for Doom 🛡️AI Safety

lesswrong.com·3h

How to build an AI Security Program ⚖️Trustworthy AI

medium.com·6d

Show HN: Prompt injection detector beats ProtectAI by 19% accuracy, 8.9x smaller 💉Prompt Injection

huggingface.co·1d·Hacker News

We Faked a Tool. It Hijacked an AI Agent and Fed Users Lies and can do so much more. 💉Prompt Injection

medium.com·17h

Loading more...