Metraipolis › archive › dc_5acaa982b207
SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system — arXiv:2608.15012
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15012
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:57:35.477Z
- SHA-256 of the archived text
2c09f6b62b6c8eb099509eb99ee2fb4e25eefd47aaff72d4cc8438510217090f- Stable URL of this page
https://metraipolis.com/documento/dc_5acaa982b207
How to cite
SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system — arXiv:2608.15012 — arXiv (en), https://arxiv.org/abs/2608.15012 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5acaa982b207 (Metraipolis archive dc_5acaa982b207, sha256 2c09f6b62b6c8eb099509eb99ee2fb4e25eefd47aaff72d4cc8438510217090f)
BibTeX
@misc{dc5acaa982b207,
title = {SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system — arXiv:2608.15012},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15012},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5acaa982b207; sha256 2c09f6b62b6c8eb099509eb99ee2fb4e25eefd47aaff72d4cc8438510217090f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15012. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The rapid advancement of large language models (LLMs) has created a growing asymmetry in cybersecurity, where attack accelerates toward autonomous execution while defense remains predominantly human-intensive. Despite substantial prior work across cyber ranges, AI-driven attack, and AI-driven defense, this asymmetry persists. We trace it to a deeper root cause, that evolution itself has stalled on both sides at three layers. To overcome this, we propose co-evolution as the integrating insight, where attack and defense AI agents autonomously and safely drive each other's evolution through adversarial confrontation. Based on this insight, we present \sysevolve, comprising three co-designed components, \sysfield, \sysspear, and \sysarmor. \sysfield constructs realistic multi-host ranges. \sysspear generates efficient, safe attack schemes. \sysarmor performs real-time, interpretable defense. Together they form a self-driven adversarial loop restoring evolution at all three layers. In evaluation, \sysfield achieves zero-loss collection at 2.1\% overhead and orchestrates 257 CVEs into 1,148 ranges, \sysspear improves attack success by over 25\% over baseline LLMs, and \sysarmor achieves 10--1000$\times$ greater precision than prior systems and detects real APT attacks in production at Huawei and Sangfor. Our evaluation also reveals three findings about LLM agent capabilities. First, multi-step composition and larger topologies expose agent capability gaps hidden by single-step evaluations. Second, the bottleneck lies after initial access in post-compromise state utilization. Third, LLM agents are susceptible to environmental interference. When decoy endpoints are deployed in the range, agent timeouts triple and downstream completion disappears despite the success rates of initial accesses are unchanged. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2608.15012 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:13.977Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).