Search papers, labs, and topics across Lattice.
This paper introduces SecRespond, a novel benchmark designed to evaluate the capabilities of Large Language Model (LLM) agents in post-compromise incident response scenarios, addressing a critical gap in existing cybersecurity assessments that focus primarily on pre-compromise conditions. The benchmark assesses agents' performance using a diverse set of cyber ranges, requiring them to generate forensic reports and remediation plans based on compromised host data. Experimental findings indicate that while LLMs can identify issues flagged by alerts, they fail to effectively investigate undetected intrusions and develop comprehensive remediation strategies, highlighting significant limitations in their current capabilities for real-world applications.
LLMs can identify flagged security issues but struggle to uncover silent intrusions and create effective remediation plans, revealing a critical gap in their utility for real-world incident response.
Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities. However, existing cybersecurity benchmarks focus on pre-compromise settings where agents are placed in a clean and idealized environment before an attack occurs. This leaves the post-compromise setting underexplored. To address this gap, we introduce SecRespond, the first benchmark for evaluating LLM agents on the post-compromise incident-response workflow. Given a forensic disk snapshot of a compromised host together with the alerts, vulnerability scans, and baseline checks reported by a host security product, agents are required to produce forensic reports on intrusions, baseline risks, and vulnerability risks, together with a remediation plan. We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host, spanning 4 entry-point types, 21 ATT&CK techniques, and 5 operating systems. We evaluate 23 frontier LLMs on the OpenCode agent harness. Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions and to produce comprehensive, verified remediation plans, with no model achieving complete detection and remediation on any single range. This reveals a fundamental bottleneck in building agents for real-world incident response. The benchmark is publicly available at https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond.
DAMO