Mutate to Bypass: Autonomous Endpoint Evasion via Knowledge-Driven Multi-Agent Orchestration
2026-08-03 • Cryptography and Security
Cryptography and SecurityOperating Systems
AI summaryⓘ
The authors created AutoBypass, a system that can automatically test if commercial security software called Endpoint Detection and Response (EDR) can be tricked by known hacking methods. They organized security knowledge into a smart database that helps the system plan and improve attacks against these protections. When tested on seven major security products, AutoBypass successfully bypassed all of them, showing it can find security gaps. Their work helps turn scattered hacking info into useful tools for ongoing, automated testing of security defenses.
Endpoint Detection and Response (EDR)EDR evasionpolymorphic codethreat intelligenceWindows DefenderTrend Micro AVknowledge baseautomated security assessmentpayload generation
Authors
Weifeng Yuan, Wenbo Guo, Qingyun Du, Jun Chen, Feng Dong, Haoyu Wang, Yang Liu
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.