🛡️ AI Security - CWhiting · Scour

AI Security Evaluation: How to Test Prompt Injection, Data Leakage, and Unsafe Tool Calls 🛡️AI Safety

·1d

Pen tests show AI security flaws far more severe than legacy software bugs 🕳LLM Vulnerabilities

csoonline.com·6d

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

castform.com·9h·Hacker News

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection 💉Prompt Injection

AI Security Lab Hub 💉Prompt Injection

arcanum-sec.github.io·4d

Researchers detail safety gaps in agentic AI systems 🛡️AI Safety

kite.kagi.com·2d

Building the Solution Teams Need to Secure AI Against Prompt Injection ⚙️LLMOps

techcommunity.microsoft.com·1d

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

msukhareva.substack.com·6d·Substack

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

·1d

AI Security Architecture: The Key to Verifiable AI 🛡️AI Safety

malware.news·3d

The Real AI Security Risk Isn't Data Leakage. It's What Your Agents Can Do 🛡️AI Safety

Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents 🧠Context Engineering

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations 🏠Local LLM Deployment

Position: AI Security Policy Should Target Systems, Not Models ⚖️AI Policy

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

arxiv.org·3d·Hacker News

The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play 🌊Stream Ciphers

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs 🕳LLM Vulnerabilities

SL5 Standard for AI Security 🛡️AI Safety

Containment Verification: AI Safety Guarantees Independent of Alignment 🔒Agentic Safety

"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking 💧Digital Watermarking

Log in to enable infinite scrolling