🔐 Systems Hardening - matmat · Scour

Sandboxing AIOps and Agentic AI Security 🔒WASM Capabilities

blog.cosmonic.com·6d·Hacker News

Endo: JavaScript plugin framework with built-in supply chain attack resistance 🔒WASM Capabilities

github.com·2d·Hacker News

How AI-native systems are built 💾Persistence Strategies

thenewstack.io·12h

The Capability-Tractability Tradeoff 🎯Performance Proofs

buttondown.com·1d

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models 🔒WASM Capabilities

Loops and Routines Without Claude ⚔️Lean Tactics

ingresslabs.net·2d·Hacker News

Understanding Bottleneck 🎯Performance Proofs

dsebastien.net·2d

oss-security - Dirty Frag: Universal Linux LPE 🔌Operating system internals

openwall.com·4d·Lobsters, Hacker News

Defense by Design: Building Infrastructure That Assumes Adversaries 🛡️Error Boundaries

backblaze.com·4d

Security By Design: The Shortcut to Smarter, Safer Systems 🔐Capability Security

nocomplexity.com·5d

Trust Is the Bottleneck 🎯Performance Forensics

blog.reqproof.com·6d·Hacker News

AI is Breaking Two Vulnerability Cultures 🔓Hacking

jefftk.com·3d·Lobsters, Hacker News

SoK: Robustness in Large Language Models against Jailbreak Attacks 🧪Binary Fuzzing

Root-Cause-Driven Automated Vulnerability Repair ✅Archive Fixity

VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns 🔒WASM Capabilities

Gray-Box Poisoning of Continuous Malware Ingestion Pipelines 🧪Binary Fuzzing

On the Hardness of Junking LLMs 🧮Kolmogorov Complexity

Tenability and Weak Semantics: Modeling Non-uniform Defense -- Extended Version 🔲Proof Irrelevance

Feedback-Normalized Developer Memory for Reinforcement-Learning Coding Agents: A Safety-Gated MCP Architecture ✨Effect Handlers

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection ⚡Proof Automation

No more posts from matmat's subscribed feeds.

Scour all 24963 feeds Learn more about Feeds

Log in to enable infinite scrolling