https://curasec.metacog.co.kr/tags/threat-investigation/Recent content in Threat-Investigation on CuraSecHugoen-usMon, 13 Jul 2026 14:30:14 +0000https://curasec.metacog.co.kr/insights/2026-07-13-sheragent-scaling-attack-investigation-in-the-wild-via-llm-e/Mon, 13 Jul 2026 14:30:14 +0000https://curasec.metacog.co.kr/insights/2026-07-13-sheragent-scaling-attack-investigation-in-the-wild-via-llm-e/<ul> <li><strong>Engineer — Skip</strong></li> <li><strong>SOC/IR — Learn:</strong> SherAgent demonstrates a 31–64% improvement in automated attack investigation success rates using LLM-driven provenance graph backtracking — useful context for teams evaluating or building AI-assisted triage workflows, though no production tool or IOCs are released here.</li> <li><strong>Leader — Learn:</strong> Research from a real SOC environment shows LLM-assisted alert triage meaningfully reduces the manual investigation backlog; relevant background for leaders assessing AI tooling investments in detection and response.</li> </ul>