2026.03/Agent Security
LAAF: Logic-layer Automated Attack Framework — A Systematic Red-Teaming Methodology for LPCI Vulnerabilities in Agentic Large Language Model Systems
H. Atta, K. Huang, K. R. Lambros, Y. Mehmood, M. Z. Baig, M. A. Rahman, M. Bhatt, et al.
Abstract
Introduces an automated framework for testing logic-layer prompt-control injection across persistent memory, retrieval pipelines, tools, and multi-stage agent lifecycles.
Where it sits
Pillar 02 — Adversarial Measurement
Where does the system actually break?
Find where systems fail under attack — harder evaluations that expose weaknesses static benchmarks miss.
Outside writing
How outside writing is graded →More from measurement
Whole pillar →2026.02Manifold of Failure: Behavioral Attraction Basins in Language ModelsMaps unsafe behavioral regions in language models as attraction basins, using quality-diversity search to expose distinct vulnerability niches and their geometry.2026.01Large Empirical Case Study: Go-Explore adapted for AI Red Team TestingAdapts Go-Explore to agent red teaming and shows that random-seed variance can dominate algorithm choices, making multi-seed evaluation essential for defensible comparisons.2025.07Logic-layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic SystemsDefines logic-layer prompt-control injection, where delayed or conditional payloads persist through memory, vector stores, and tool-connected agent systems.