5,445 件 ・ 関連度順
概要と使いどころ
Add or verify a model's chat prompt rendering and tokenization in rust/sglang-processor so it matches SGLang's Python serving path exactly (same prompt text, same token ids). Use when adding a model to sglang-processor, porting a model's rendering from sgl-router, bumping Dynamo's renderer, or debugging a processor-vs-Python prompt mismatch.
日本語の概要は準備中です。原文の説明を表示しています。
How SGLang's runtime configuration and process-global state are organized (RuntimeContext tiers, publish + namespace config bags, the pristine ServerArgs seed, override entry points, resource/stream/buffer leases, per-forward flags), the CI guardrails that enforce the design, and the idioms for developing and testing against it. Load this before touching server_args, model overrides, module-level state, or per-forward state in sglang.
日本語の概要は準備中です。原文の説明を表示しています。
Compute the optimal --mamba-full-memory-ratio (or --max-mamba-cache-size pin) for a hybrid attention + linear-attention (Mamba / GDN / KDA) model's two serving memory pools, from the workload and serving config. Use when a user asks what ratio to set, why concurrency is clamped, or how to size the state vs KV pools for a hybrid model.
日本語の概要は準備中です。原文の説明を表示しています。
Export backtest strategies to indicator/strategy code for major trading platforms — TradingView, 通达信, 同花顺, 东方财富, MT5.
日本語の概要は準備中です。原文の説明を表示しています。
Market microstructure: bid-ask spread analysis, order-flow toxicity metrics (VPIN / Kyle lambda), liquidity measures (Amihud / Roll), price-impact models, limit-order-book analysis, and China A-share call auction / block trade mechanics.
日本語の概要は準備中です。原文の説明を表示しています。
Deep management assessment — the 'buying a stock is buying a person' layer. For a company or a named executive, evaluate integrity (promise-vs-delivery tracking, crisis behavior, stakeholder treatment), ability (strategic foresight, execution, capital-allocation record) and governance (equity structure, compensation, related-party deals). Outputs a weighted score across integrity / ability / capital-allocation / governance plus Duan Yongping's 3-question verdict ('would you hand this person your money for 10 years'). Use when standard research leaves management quality uncertain, or when management IS the investment thesis.
日本語の概要は準備中です。原文の説明を表示しています。
Detect privilege escalation attempts across Windows and Linux, including access token manipulation, UAC bypass, unquoted service path abuse, kernel exploits, and sudo/doas abuse. Use when threat hunting for T1068-style privilege escalation, triaging EDR/SIEM alerts on suspicious privilege changes, scoping compromise during incident response, or validating detection coverage in a purple team exercise.
日本語の概要は準備中です。原文の説明を表示しています。
Exploits privileged pods, host mounts, runC CVEs, and exposed Docker sockets to break out of a container and reach the underlying host during an authorized container-security assessment. Use when executing an approved breakout test, demonstrating the real impact of a privileged or hostPath workload, or validating that escape mitigations actually hold. Keywords: container breakout, privileged, hostPath, docker.sock, runC CVE-2019-5736, CVE-2024-21626, release_agent, nsenter. Do not use for defensive detection of these techniques - use detecting-container-escape-attempts.
日本語の概要は準備中です。原文の説明を表示しています。
Hunt for suspicious PowerShell execution (T1059.001) such as encoded commands, download cradles, AMSI bypass, and constrained language mode evasion using EDR telemetry (CrowdStrike, Microsoft Defender for Endpoint), Sysmon, and SIEM queries (Splunk, Elastic). Use when proactively threat hunting, triaging EDR/SIEM alerts, or scoping an incident involving malicious PowerShell activity.
日本語の概要は準備中です。原文の説明を表示しています。
Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.
日本語の概要は準備中です。原文の説明を表示しています。
Detect compromised cloud credentials across AWS, Azure, and GCP by analyzing anomalous API activity, impossible-travel patterns, and credential-stuffing indicators using GuardDuty, Microsoft Defender for Identity, and Google SCC Event Threat Detection. Use when investigating alerts about cloud API activity from unfamiliar locations, responding to an exposed-credential notification, or scoping a credential compromise.
日本語の概要は準備中です。原文の説明を表示しています。
Detect lateral movement in network traffic using Zeek (formerly Bro) log analysis. Parses conn.log, smb_mapping.log, smb_files.log, dce_rpc.log, kerberos.log, and ntlm.log to identify SMB file transfers, NTLM account spray activity, remote service execution, and anomalous internal connections.
日本語の概要は準備中です。原文の説明を表示しています。
Detect Layer 2 ARP poisoning/spoofing by deploying ARPWatch, Dynamic ARP Inspection (DAI), Wireshark packet analysis, and custom Python monitoring scripts that flag gratuitous ARP floods, IP-to-MAC mapping changes, and duplicate IP addresses. Use when investigating suspected man-in-the-middle interception or session hijacking on a local network segment, or when building layer-2 anomaly detection for a SOC.
日本語の概要は準備中です。原文の説明を表示しています。
Correlates disparate security incidents, IOCs, and adversary behaviors across time and organizations to identify unified threat campaigns, attribute them to common threat actors, and extract shared indicators for improved detection. Use when multiple incidents exhibit overlapping indicators, when sector-wide attack campaigns require cross-organizational analysis, or when building campaign-level intelligence products. Activates for requests involving campaign analysis, incident clustering, cross-organizational IOC correlation, or MISP correlation engine.
日本語の概要は準備中です。原文の説明を表示しています。
Design and execute a social engineering penetration test combining OSINT-driven target profiling with phishing, vishing, smishing, and physical pretexting campaigns using tools like GoPhish, the Social Engineer Toolkit (SET), and Evilginx to measure human security resilience. Use when scoping or running an authorized human-attack-surface test and reporting results to identify security awareness training gaps.
日本語の概要は準備中です。原文の説明を表示しています。
Plan, run, and measure an adversary engagement operation using the MITRE Engage framework so that deployed deception is driven by strategy instead of deployed ad hoc. Covers the Engage Matrix (Prepare, Expose, Affect, Elicit, Understand), the 10-Step Operational Process, mapping engagement Activities to the ATT&CK techniques they expose, and defining measurable Goals and Operational Objectives. Use when a team has honeypots, honeytokens, or canary tokens but no coordinating strategy, when leadership asks "should we engage attackers and how", when building a deception/denial program, when writing an adversary engagement operation plan, or when deciding which deception Activities to deploy against a specific threat actor. Keywords: MITRE Engage, adversary engagement, cyber deception strategy, denial and deception, Engage Matrix, EAC, EGO, Expose Affect Elicit, deception program, honeypot strategy, engagement operation.
日本語の概要は準備中です。原文の説明を表示しています。
Run a targeted spearphishing simulation for initial access by developing OSINT-derived pretexts, building payloads (HTML smuggling, macro docs, ISO/LNK, OneNote, QR codes), standing up look-alike-domain email infrastructure with SPF/DKIM/DMARC via GoPhish, and tracking results. Use in authorized engagements to gain initial access via personalized phishing against specific individuals, distinct from broad campaigns.
日本語の概要は準備中です。原文の説明を表示しています。
Plants Canarytokens-based decoy artifacts (honey credentials, DNS tokens, web-bug URLs, AWS keys, documents, kubeconfigs) using Thinkst's open-source Canarytokens project and alerts via email or webhook when a token is touched. Use for high-fidelity intrusion detection in low-telemetry areas like file shares or credential stores, or to catch credential dumping and data-theft staging.
日本語の概要は準備中です。原文の説明を表示しています。
Configures pfSense firewall rules, NAT policies, IPsec/OpenVPN tunnels, and traffic shaping to enforce network segmentation and control traffic between zones such as DMZ, internal, guest, and IoT. Use when deploying a pfSense perimeter or internal firewall, setting up port-forwarding NAT, configuring site-to-site or remote-access VPNs, or applying QoS/bandwidth policies.
日本語の概要は準備中です。原文の説明を表示しています。
Apply bottom-up and top-down role mining techniques, including clustering algorithms and formal concept analysis, to discover optimal RBAC roles from existing user-permission assignments, consolidating overlapping roles and enforcing least privilege. Use when an identity program needs to reduce role explosion or redesign its RBAC role set from access data.
日本語の概要は準備中です。原文の説明を表示しています。
Perform DCSync attacks by abusing MS-DRSR replication rights (DS-Replication-Get-Changes/-All) to impersonate a Domain Controller and extract KRBTGT, Domain Admin, and service account hashes for Golden Ticket forging, typically with Mimikatz. Use in authorized engagements after finding principals with replication rights, to establish long-term domain persistence, or to validate detections for replication abuse.
日本語の概要は準備中です。原文の説明を表示しています。
Build threat actor profiles by collecting OSINT from vendor reports, paste sites, dark web forums, social media, and code repos, correlating indicators, mapping adversary infrastructure with tools like Maltego and SpiderFoot, and producing structured dossiers of motivations, capabilities, infrastructure, and TTPs. Use when performing attribution or building an adversary dossier from open-source intelligence.
日本語の概要は準備中です。原文の説明を表示しています。
Generate forensic super-timelines with Plaso's log2timeline.py, pinfo.py, psort.py, and psteal.py CLI tools (fusing file-system MACB, registry, EVTX, browser history, prefetch, LNK, and more), then triage and filter the results in Timesketch. Use when reconstructing the full sequence of events on a compromised or forensically imaged host during a DFIR investigation.
日本語の概要は準備中です。原文の説明を表示しています。
Build a systematic threat-hunt workflow that turns threat intelligence and ATT&CK gap analysis into testable hypotheses, then executes and validates them via EDR/SIEM queries (CrowdStrike, Defender, Splunk, Elastic, Sysmon, Velociraptor, Sigma) and documents findings in a standardized hunt report. Use when planning or running a proactive threat hunt or scoping compromise from an intel- or anomaly-driven lead.
日本語の概要は準備中です。原文の説明を表示しています。