Policy dependency / Stack layer
Build Integration, Not Fuzzing, Is What Kills LLM Dynamic Analysis on Real Autonomous-Vehicle Stacks
arXiv 2608.13450
Stack layer / Threat pattern
Two-Tier 'Librarian + Writer' Architecture Removes 6,845 Cross-Section Contradictions From LLM Research Reports to Zero
arXiv 2608.12984
Stack layer / Threat pattern
HARD Turns LLM Agent Runtime Defense Into a Self-Evolving Loop Instead of Hand-Written Rules
arXiv 2608.12977
Stack layer / Threat pattern
HARD: let the agent evolve its own runtime defenses instead of hand-writing guardrails
arXiv
Stack layer / Threat pattern
Coins: Evaluating LLM Formal Specifications by Instantiating Them on Trusted Test Cases Instead of Proving Equivalence
arXiv 2608.13077
Policy dependency / Threat pattern
TopoIntent Compiles Natural-Language Security Intent Into Runnable Mininet Topologies With iptables ACLs
arXiv 2608.13389
Stack layer / Threat pattern
Iterative LLM Infrastructure-as-Code Repair Silently Breaks Security Checks in 3.3% of Scenarios; Stop at Iteration 3
arXiv 2608.13404
Stack layer / Threat pattern
Preregistered experiment finds structured spec contracts do not beat narrative prose for code generation
arXiv 2608.10314