Researchers introduce ALERT-BENCH, requiring agents to investigate detector-generated alerts through a live SIEM over replayed public telemetry. On the main 1,247-alert sample, five reasoning approaches each miss at least 40.4% of attack-related alerts, while the authors’ AIDA architecture reduces the false-negative rate to 3.1% under the same GPT-4.1 configuration, with more alerts escalated to analysts. Additional scenario and model tests remain within the studied dataset family; analyst use and independent SOC validation are untested.
SOC automation
Triage, detection engineering, and analyst assistance.
Use the arrow keys to move between records, Home and End to jump to the first and last, and Enter to select one.
Select a mark to read the record. Mark size shows editorial significance. Hollow marks are dated to the month. Era bands are editorial labels.
Records in view
14 records · newest firstZhongguancun Laboratory researchers introduce APTInvestBench, built from report-informed attack reconstructions under varied log-collection conditions. In their ten-scenario comparison of eleven models, agents acquire sufficient evidence for 44.3% of recoverable attack actions on average, but their formal citations support 25.0%; similar aggregate citation coverage can conceal losses of support for actions that remain recoverable. These are controlled benchmark investigations, not measurements of deployed SOC performance.
Chen and colleagues (arXiv v1, under review for ICLR 2027) introduce CyberClear, 450 instances built from public APT log datasets in which an agent must turn long defender logs, without prior attack clues, into a provenance graph with ATT&CK-mapped steps. References were generated by an LLM and passed automatic verification and expert review; scoring compares graph code with five LLM-judge dimensions. They also propose CyberProvenance, a multi-agent harness that reproduces predicted attack steps in isolated lab environments and refines the graph, and report it best on most semantic metrics while the highest Strict score remains 0.6477 out of 1.
Dave Chismon, the NCSC's CTO for Architecture, argues that offensive problems are mostly technical with clear success states while defensive problems are mostly organizational, so defenders cannot put AI to work as attackers can and agentic defense may struggle to keep pace with AI-enabled attacks. He proposes rating a defensive action's riskiness on five dimensions (potency, scope, criticality, rollout confidence, recoverability) and starting with low-potency tasks where AI advises a human. The post also says the NCSC and DCMS are working on a national-scale agentic cyber defence ecosystem called Cyber Shield and that the NCSC seeks research on proving low-risk actions are low risk.
University of South Florida researchers embedded in a working SOC for over a year built and deployed an LLM-based agentic companion to handle high-volume, low-priority tickets, with analysts using it in the final four months. They report that companion outputs were reused in analysts' closing reports in more than 90% of cases, and that analysts who shaped the companion's behaviour came to trust it more.
Researchers evaluate security agents at fixed cost levels on offensive Cybench challenges and defensive Splunk BOTS v1 investigations, splitting spend into inference and tool use. They find offensive success rises with test-time compute, while defensive investigation depends more on disciplined tool use and telemetry navigation, and argue benchmarks should report cost and operational fit alongside success.
A technical report from security vendor Simbian AI presents the Cyber Defense Benchmark, which asks agents to hunt through 75,000-135,000 raw Windows event log records per episode, with no guiding questions, and flag the timestamps of malicious events drawn from 106 OTRF attack procedures. In the first version, the best of five frontier models (Claude Opus 4.6) flagged only 3.8% of malicious events on average and no model met the authors' bar of 50% recall on every ATT&CK tactic. A revision two days later, with more models and a new coverage metric, reached the same no-pass conclusion.
CTI-REALM places agents in a tool-rich environment where they read threat intelligence reports, explore telemetry, iterate KQL queries and produce Sigma and KQL detection rules across Linux, AKS and Azure cloud scenarios. The paper's evaluation of 16 model configurations found Claude Opus 4.6 (High) best at 0.637, with cloud detection hardest; Microsoft's blog later added an early Claude Mythos Preview snapshot scoring 0.685.
Microsoft reports a randomized controlled trial of its own Security Copilot Phishing Triage Agent. In the trial, 167 external security analysts each triaged a 25-email queue drawn from a curated corpus of emails reported by Microsoft employees. In the scenario where the agent classified every corpus email correctly, analysts with the agent found 6.5 times as many true positives per minute as the control group and scored 77% higher on F1; with the agent's accuracy set to 80% and a 20% malicious rate, the productivity gain fell to 3.1 times. Analysts with the agent spent 53% more time on malicious emails and did not simply confirm its malicious verdicts, but they were more likely to accept its benign verdicts, including planted false negatives.
CyberSOCEval adds two open-source SOC benchmarks to CyberSecEval 4: malware analysis questions built from sandbox detonation reports, and threat intelligence reasoning over unstructured reports. The authors find larger, newer models do better, reasoning models gain less than in coding and math, and current models are far from saturating the tasks.
Microsoft Research describes Project Ire, a prototype LLM agent that uses decompilers and binary analysis tools to reverse engineer software and classify it as malicious or benign, producing an auditable chain-of-evidence report. Microsoft reports 0.98 precision and 0.83 recall on a Windows driver dataset, but 0.26 recall on about 4,000 hard real-world files, and plans to deploy it in Defender as Binary Analyzer.
ExCyTIn-Bench builds threat-investigation questions from graphs of security logs collected in a controlled Azure tenant with simulated multi-step attacks, and asks agents to query the logs to answer them. In the July 2025 version the best model (o4-mini) reached a reward of 0.368; in the May 2026 revision, accepted at ICML 2026, the best (Claude Opus 4.5) reached 0.606, which the authors say leaves substantial headroom.
Google announced Sec-Gemini v1, an experimental model combining Gemini with Google Threat Intelligence, OSV and Mandiant data for tasks such as incident root-cause analysis and vulnerability impact assessment. Google reports it outperforms other models by at least 11% on CTI-MCQ and 10.5% on CTI-Root Cause Mapping, and offered free research access to selected organizations.
Microsoft announced Microsoft-built Security Copilot agents, including a Phishing Triage Agent in Defender, alert triage agents in Purview, a Conditional Access Optimization Agent, a Vulnerability Remediation Agent in Intune and a Threat Intelligence Briefing Agent, plus five partner agents. Preview was planned from April 2025; the announcement contains no evaluation of agent accuracy.