Mutate to Bypass: Autonomous Endpoint Evasion via Knowledge-Driven Multi-Agent Orchestration

2026-08-02

AI Summary

This work addresses the challenge of transforming fragmented public security knowledge into effective payloads and continuously refining them based on ambiguous alerts to evaluate the real-world defensive capabilities of commercial EDR systems. The authors propose AutoBypass, the first closed-loop framework that integrates structured threat intelligence with a multi-agent collaboration mechanism. AutoBypass leverages a detection-aware knowledge base to drive attack planning, polymorphic code generation, and binary compilation, while dynamically optimizing its evasion strategies through telemetry feedback. Experimental results demonstrate that the approach achieves a 100% bypass rate across seven leading EDR products, with Windows Defender at 90% and Trend Micro at 86.7%. Furthermore, the constructed knowledge base elevates the success rate of an 8B open-source model to 43–83%, approaching the performance of proprietary large language models.

Abstract

Public reports and open-source resources expose many EDR evasion techniques, but it remains unclear whether commercial Endpoint Detection and Response (EDR) systems can withstand these documented attacks. Evaluating them requires turning fragmented security knowledge into working payloads and refining those payloads from opaque alerts, tasks that existing automation does not address. We present AutoBypass, a knowledge-grounded, closed-loop multi-agent framework for automated EDR resilience assessment. A Detection-Aware Knowledge Base structures threat intelligence, expert analyses, and open-source proofs of concept into evasion techniques and operational constraints. Agents use this knowledge to plan attacks, generate polymorphic code, and compile binaries, while a telemetry-driven reasoning engine diagnoses failures and feeds corrective evidence back into the strategy. Across seven commercial endpoint security platforms, AutoBypass bypassed every target, reaching 90% evasion against Windows Defender and 86.7% against Trend Micro AV. Ablations show that the knowledge base raises the success rates of 8B open-weight models from 27--53% to 43--83%, bringing them close to large proprietary models. These results demonstrate a systematic way to operationalize public security knowledge for continuous, automated assessment of EDR resilience.

Problem

• EDR evasion
• endpoint security
• automated assessment
• threat intelligence
• resilience evaluation

Innovation

• multi-agent orchestration
• knowledge-driven evasion
• EDR bypass
• polymorphic code generation
• closed-loop automation