Skip to main content
Didit 融资 750 万美元，打造身份与欺诈基础设施
Didit
机器人检测

使用被动活体检测网关阻止机器人。一帧图像。一个决策。

在高价值操作前进行一次被动活体检测。机器人没有面部可供识别，因此无法通过。2 秒内出结果，每次检测 $0.10，每月免费 500 次。

免费开始阅读文档
投资方
Y CombinatorRobinhood Ventures
GBTC Finance
Bondex
Crnogorski Telekom
UCSF Neuroscape
Shiply
Adelantos

全球2,000多家组织信赖。

一个抽象的暗色机器人检测堆栈, 四个浮动的半透明暗玻璃面板以 3D 透视方式呈现在纯黑色背景上，由一条发光的 Didit 蓝色垂直线贯穿，并由发光的扫描仪支架框住。每个面板上都有一个微小的浅白色抽象网关图案（机器人头部、平面波形、异常网格、可疑计时）。

为什么 CAPTCHA 不再有效

破解农场能绕过 CAPTCHA。但活体检测仍需人脸。

商业 CAPTCHA 破解农场只需几美分就能破解 hCaptcha 和 reCAPTCHA Enterprise。被动活体检测需要脚本无法拥有的东西, 一个真实的人站在真实的摄像头前。每次网关检测 $0.10，2 秒内出结果，每月免费 500 次。

工作原理

从注册到验证用户，仅需四步。

  1. 步骤 01

    创建工作流

    选择您需要的检查项, 身份、活体、人脸比对、制裁名单、地址、年龄、电话、邮箱、自定义问题。在仪表盘中将它们拖入工作流，或通过我们的 API 发布相同的工作流。根据条件进行分支，运行 A/B 测试，无需代码。

  2. 步骤 02

    集成

    使用我们的 Web、iOS、Android、React Native 或 Flutter SDK 进行原生嵌入。重定向到托管页面。或者直接通过电子邮件、短信、WhatsApp 等任何方式向用户发送链接。选择适合您技术栈的方式。

  3. 步骤 03

    用户完成流程

    Didit 负责托管摄像头、灯光提示、移动端切换和辅助功能。在用户进行流程时，我们实时评估 200 多个欺诈信号，并根据权威数据源验证每个字段。两秒内出结果。

  4. 步骤 04

    您接收结果

    实时签名 Webhook 可确保用户批准、拒绝或发送审核后，您的数据库立即同步。按需轮询 API。或者打开控制台检查每个会话、每个信号，并按您的方式管理案例。

为网关而生 · 基础设施定价

一次被动活体检测。$0.10 每次网关检测。

机器人网关是一个组合, 界面、预筛选、活体检测、决策。在工作流构建器中，为每个工作流切换不同的模块。
阅读文档获取 API 密钥
01 · 攻击面

机器人出没之处, 以及设防之地。

注册表单、排行榜、空投/代币申领、推荐奖励、评论区、票务队列。相同的工作流构建器可保护所有界面。仅在真正重要的操作上触发, 日常读取无需网关。
工作流编排模块
02 · 活体检测网关

摄像头前，真人实拍。

被动活体检测要求用户保持静止一帧。模型在两秒内返回结果，每次检测 $0.10。没有谜题，没有字符识别，没有行为鼠标轨迹, 只有一帧图像和一个决策。iBeta Level 1 PAD 认证，符合 ISO/IEC 30107-3 标准。
活体检测模块
03 · 攻击向量防御

所有机器人攻击向量, 统一判决。

脚本化提交的无头 Chrome、浏览器自动化农场、虚拟摄像头 AI 人脸注入器、预录屏幕回放、无摄像头仅图像提交、AI 生成的深度伪造, 全部被阻止。该模型每年都会在 iBeta 独立重新测试，以应对野外出现的新攻击向量。
活体检测工作原理
04 · IP + 设备预筛选

对明显是机器人的跳过摄像头验证。

设备和 IP 分析返回 0-100 分，以及 VPN、Tor、数据中心自治系统号 (ASN)、无头浏览器和设备速度标志。每次调用 $0.03，100 毫秒内完成。当网络明显是脚本时，提前拒绝；只在可信的人类身上花费活体检测预算。
设备与 IP 分析模块
05 · 可复用 KYC 重放

一次真人，永远真人。

已通过 Didit 验证会话的用户，可通过 Reusable KYC 免费复用凭证。无需二次摄像头授权，零摩擦, 仅对未知流量设防。永久免费。
Reusable KYC 模块
06 · Webhook 管道

签名判决。三条分支。搞定。

带签名的 Webhook 会返回结果, Approved（通过）、Declined（拒绝）、In Review（审核中）、Not Finished（未完成）。在读取正文前，请使用基于哈希的消息认证码 (HMAC) SHA-256 验证 X-Signature-V2。免费提供 200 多个欺诈信号。据此调整原始操作。
Webhook 参考
集成

一个会话。一个签名结果。三个分支。

打开网关。读取签名结果。允许、阻止或邀请重试。
POST /v3/session/活体检测
$ curl -X POST https://verification.didit.me/v3/session/ \
  -H "x-api-key: $DIDIT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "workflow_id": "wf_bot_gate",
    "vendor_data": "signup-918",
    "metadata": { "surface": "signup_form" }
  }'
201已创建{ "session_url": "verify.didit.me/..." }
在 webhook 返回 status: Approved 之前阻止操作。文档 →
POST /webhooks/didit判决
// X-Signature-V2 verified upstream
if (payload.status === "Approved") {
  allowSignup(payload.vendor_data);
} else if (payload.status === "已拒绝") {
  throttleIP(payload.ip_analysis.ip);
  blockAndLog(payload.vendor_data);
}
200OK状态：已批准 · 已拒绝 · 审核中 · 未完成
读取 payload 前验证 X-Signature-V2。文档 →
代理就绪集成

一键部署被动活体检测机器人门禁。

粘贴到 Claude Code、Cursor、Codex、Devin、Aider 或 Replit Agent。填写您的技术栈。代理将连接触发器，启动活体检测会话，验证 webhook，并控制操作。
didit-integration-prompt.md
You are integrating Didit Passive Liveness as a bot-gate on a high-value action — sign-up, leaderboard submission, airdrop / token claim, referral payout, comment, or ticket queue. Bots cannot pass Passive Liveness because they have no face to present to the camera. One API call. One signed webhook. One decision.

WHY THIS SHAPE
  - Bots scale because they cost nothing per attempt. CAPTCHA stops the dumbest ones but commercial solver farms beat hCaptcha and reCAPTCHA Enterprise at fractions of a cent per solve.
  - Passive Liveness asks for something a script does not have: a live human face in front of a real camera. The model decides on one frame, in under two seconds, with no user interaction beyond "hold still".
  - $0.10 per check (Passive Liveness module). 500 verifications free every month. Combine with $0.03 IP / device pre-screen to keep the camera off the obvious bots and the budget on real candidates.

PRE-REQUISITES
  - Production API key from https://business.didit.me (sandbox key in 60 seconds, no credit card).
  - A webhook endpoint with HMAC SHA-256 verification of the X-Signature-V2 header using your webhook secret.
  - A Workflow Builder workflow containing the Passive Liveness module — optionally Device & IP Analysis pre-step.
  - The high-value action wrapped in a server-side gate that defaults to BLOCK and only unblocks on a verified webhook with status: Approved.

STEP 1 — (Optional) Cheap IP / device pre-screen
  Before opening a camera, score the network with Device & IP Analysis ($0.03 / call, under 100ms).
  If the score is low and no datacenter / VPN / scripted-user-agent flags fire, run Step 2.
  If the score is high or any of those flags fire, skip the liveness call and decline up-front — this saves the camera budget for plausible humans.

STEP 2 — Open a Passive Liveness session
  POST https://verification.didit.me/v3/session/
  Headers:
    x-api-key: <your api key>
    Content-Type: application/json
  Body:
    {
      "workflow_id": "<wf id with the Passive Liveness module>",
      "vendor_data": "<your action / user id, max 256 chars>",
      "callback": "https://<your-app>/bot-gate/callback",
      "metadata": {
        "surface": "signup_form",
        "action_id": "<your internal reference>"
      }
    }

  Response: 201 Created with a hosted session URL. Redirect inline (web) or open in a Software Development Kit (SDK) webview (mobile). The action stays BLOCKED on your side until the signed webhook lands.

STEP 3 — Read the signed webhook
  Didit POSTs the verdict. Verify X-Signature-V2 (HMAC SHA-256 of the raw body using your webhook secret) BEFORE reading the JSON.

  Payload (excerpted):
    {
      "session_id": "<uuid>",
      "vendor_data": "<your action / user id>",
      "status": "Approved",
      "liveness": { "status": "Approved" }
    }

  Session status enum (exact case, Title Case With Spaces): Approved | Declined | In Review | Resubmitted | Expired | Not Finished | Kyc Expired | Abandoned.

STEP 4 — Branch the action
  Approved      → allow the sign-up / claim / submission.
  Declined      → block the action. Log liveness warnings (image-only / virtual-cam / replay / deepfake) and throttle the source IP.
  Not Finished  → invite the user to retry with a fresh session URL.
  Expired       → session timed out. Resend the link.
  Abandoned     → the user closed the flow before completing. Resend the link.

STEP 5 — (Optional) Replay Reusable Know Your Customer (KYC) for known humans
  If a user has previously completed a Didit-verified session, a fresh liveness check is not required for re-entry — they can replay their verified credential at no cost via Didit Reusable KYC. Use the user's existing session_id to confirm enrollment and skip Step 2. Free forever.

WEBHOOK EVENT NAMES
  - Sessions: standard session webhook. One endpoint, status field tells you where in the lifecycle.
  - Verify X-Signature-V2 (HMAC SHA-256) on every payload.

WHAT GETS BLOCKED
  - Headless Chrome with scripted form submission
  - Browser-automation farms (Puppeteer, Playwright, Selenium)
  - Image-only submissions (no camera attached)
  - Virtual-camera AI face injectors
  - Pre-recorded screen replays
  - Print or paper attacks
  - Silicone / latex masks
  - AI-generated deepfake faces

  All independently tested at iBeta and certified at Level 1 Presentation Attack Detection (PAD) against the full ISO/IEC 30107-3 catalogue. Re-tested every year.

CONSTRAINTS
  - Session statuses use Title Case With Spaces. Never use UPPER_SNAKE_CASE for session verdicts — that's the Transactions API.
  - Default to BLOCK on the server. Only unblock when the verified webhook says Approved.
  - 200+ fraud signals are evaluated on every session at no extra cost — read them off the decision payload, don't re-query.

Read the docs:
  - https://docs.didit.me/sessions-api/create-session
  - https://docs.didit.me/core-technology/liveness/overview
  - https://docs.didit.me/core-technology/ip-analysis/overview
  - https://docs.didit.me/core-technology/reusable-kyc/overview
  - https://docs.didit.me/integration/webhooks

Start free at https://business.didit.me — sandbox key in 60 seconds, 500 verifications free every month, no credit card.
需要更多上下文？请参阅完整的模块文档。docs.didit.me →
合规性设计

一键开启新国家/地区业务。 我们为您解决难题。

我们负责设立当地子公司、获取许可证、进行渗透测试、获得认证，并与所有新法规保持一致。要在新国家/地区发布验证服务，只需轻点开关。已覆盖220多个国家/地区，每个季度进行审计和渗透测试, 是唯一一个被欧盟成员国政府正式认定比线下验证更安全的身份提供商。
阅读安全与合规性档案
欧盟金融沙盒
Tesoro · SEPBLAC · BdE
ISO/IEC 27001
信息安全 · 2026
SOC 2 · Type I
AICPA · 2026
iBeta Level 1 PAD
NIST / NIAP · 2026
GDPR
EU 2016/679
DORA
EU 2022/2554
MiCA
EU 2023/1114
AMLD6 · eIDAS 2.0
原生符合欧盟标准

数据证明

数据证明
  • iBeta L1
    独立认证的演示攻击检测, 每年重新测试。
  • <0s
    入门级安卓设备上的端到端验证。
  • $0.00
    每次被动活体检测。可选的 IP 预筛查额外收费 $0.03。
  • 0
    每个账户每月免费验证。
三个层级，一份价目表

免费开始。按使用量付费。可扩展至企业级。

每月 500 次免费验证，永久有效。生产环境按量付费。企业版提供定制合约、数据驻留和 SLA (Service Level Agreements)。
免费

免费

每月 $0。无需信用卡。

  • 免费 KYC 套件（身份验证 + 被动活体检测 + 人脸匹配 + 设备与 IP 分析）, 每月 500 次，永久有效
  • 黑名单用户
  • 重复检测
  • 每次会话 200+ 欺诈信号
  • Didit 网络中可重复使用的 KYC
  • 案件管理平台
  • 工作流构建器
  • 公开文档、沙盒、SDK、MCP（模型上下文协议）服务器
  • 社区支持
免费开始
最受欢迎
按用量付费

按用量计费

按实际用量付费。25+模块。公开的模块定价，无每月最低费用。

  • 完整KYC $0.33（身份+生物识别+IP/设备）
  • 10,000+ AML数据集, 制裁、PEP、负面媒体
  • 1,000+ 政府数据源用于数据库验证
  • 交易监控 $0.02/笔交易
  • 实时KYB $2.00/家企业
  • 钱包筛选 $0.15/次检查
  • 白标验证流程, 您的品牌，我们的基础设施
查看完整价格列表免费开始
企业版

企业版

定制MSA和SLA。适用于大批量和受监管项目。

  • 年度合同
  • 定制MSA、DPA和SLA
  • 专属Slack和WhatsApp频道
  • 按需人工审核员
  • 经销商和白标条款
  • 独家功能和合作伙伴集成
  • 指定CSM、安全审查、合规支持
联系我们

免费开始 → 仅在检查运行时付费 → 解锁企业版以获取定制合约、SLA 或数据驻留。

FAQ

常见问题

What is Didit?

Didit is infrastructure for identity and fraud, the platform we wished existed when we were building products ourselves: open, flexible, and developer-friendly, so it works as a real part of your stack instead of a black box you integrate around.

One API covers verifying people (KYC, know your customer), verifying businesses (KYB, know your business), screening crypto wallets (KYT, know your transaction), and monitoring transactions in real time, on a stack built to be:

  • Fast, sub-2-second p99 on every session
  • Reliable, in production with 1,500+ companies across 220+ countries
  • Secure, SOC 2 Type 1, ISO 27001, GDPR-native, and formally attested by Spain's financial regulator as safer than verifying someone in person

The footprint underneath: 14,000+ document types in 48+ languages, 1,000+ data sources, and 200+ fraud signals on every session. The Didit infrastructure dynamically learns from every session and gets better every day.

What counts as a bot in this context?

Anything that submits a form, claims a payout, posts a comment, or buys a ticket without a real human in the loop. Common shapes:

  • Headless browsers scripted with Puppeteer, Playwright, Selenium
  • Browser-automation farms running thousands of cheap residential proxies
  • AI bots with virtual cameras feeding generated faces into a sign-up flow
  • API scripts calling your back-end directly with stolen or guessed payloads

The defining trait is the same: nobody is looking at the screen, so nobody is in front of the camera.

Why has CAPTCHA stopped working?

CAPTCHA solver farms beat hCaptcha and reCAPTCHA Enterprise for fractions of a cent per solve. The economics flipped years ago, a 1,000-account attack costs the attacker less than your monthly Software-as-a-Service (SaaS) bill for the CAPTCHA itself.

The deeper problem is that CAPTCHA tests a skill (image recognition, character recognition, click patterns) that machines now do better than humans. A bot-gate has to test something machines do not have. A live human face in front of a real camera is exactly that.

How fast is the verification for my end user?

The full flow normally takes under 30 seconds end-to-end, pick up the ID, snap the document, snap the selfie, done. That is the fastest in the market. Legacy KYC providers usually take more than 90 seconds for the same flow.

On the back end, Didit returns the result in under two seconds at p99, measured from the moment the user finishes the selfie to the moment your webhook fires. Mobile capture is tuned for slow phones and slow networks: progressive image compression, lazy software development kit load, and a one-tap hand-off from desktop to phone via QR code if the user starts on web.

What attack vectors does it actually block?

Every common bot vector:

  • Headless Chrome with scripted form submission
  • Browser-automation farms (Puppeteer, Playwright, Selenium)
  • Image-only submissions with no camera attached
  • Virtual-camera AI face injectors feeding generated frames
  • Pre-recorded screen replays from a second device
  • Print / paper held up to the camera
  • Silicone / latex masks worn by a human accomplice
  • AI-generated deepfakes of a target account owner

All caught at the Passive Liveness layer. Nothing for the bot to feed in.

What happens if a user fails, abandons, or expires?

Every session lands on one of seven clear statuses, so your code always knows what to do:

  • Approved, every check passed. Move the user forward.
  • Declined, one or more checks failed. You can allow the user to resubmit the specific failed step (for example, re-take the selfie) without re-running the whole flow.
  • In Review, flagged for compliance review. Open the case in the console, see every signal, decide approve or decline.
  • In Progress, user is mid-flow.
  • Not Started, link sent, user has not opened it yet. Send a reminder if it sits too long.
  • Abandoned, user opened the link but did not finish in time. Re-engage or expire.
  • Expired, the session link aged out. Create a new session.

A signed webhook fires on every status change, so your database always stays in sync. Abandoned and declined sessions are free.

Where does my customer data live and how is it protected?

Production data is processed and stored in the European Union by default, on Amazon Web Services. Enterprise contracts can request alternative regions for jurisdictions whose regulators require it.

Encryption everywhere. AES-256 at rest across every database, object store, and backup. Transport Layer Security 1.3 in transit on every API call, webhook, and Business Console session. Biometric data is encrypted under a separate Customer Master Key.

Retention is yours to control. Default retention is indefinite (unlimited) unless you configure shorter, between 30 days and 10 years per application, and you can delete any individual session at any time from the dashboard or the API.

Certifications: SOC 2 Type 1 (Type 2 audit in progress), ISO/IEC 27001:2022, iBeta Level 1 PAD, and a public attestation from Spain''s Tesoro / SEPBLAC / CNMV that Didit''s remote identity verification is safer than verifying someone in person. Full report at /security-compliance.

Is Didit compliant for my industry?

Didit ships compliant by default for the regulators that matter to identity infrastructure:

  • GDPR + UK GDPR, controller / processor split, full Data Processing Agreement published, lead supervisory authority named (Spain''s AEPD).
  • AMLD6 + EU AML Single Rulebook, 1,300+ sanctions, politically exposed person, and adverse-media lists screened in real time.
  • eIDAS 2.0, EU Digital Identity Wallet aligned; reusable-identity ready.
  • MiCA (Markets in Crypto-Assets), ready for crypto on-ramps, exchanges, and custodians.
  • DORA, Digital Operational Resilience Act, EU financial-services operational resilience.
  • BIPA, CUBI, Washington HB 1493, CCPA / CPRA, US biometric privacy (Illinois, Texas, Washington) and California consumer privacy.
  • UK Online Safety Act, age-gating and child-safety obligations.
  • FATF Travel Rule, originator and beneficiary data on crypto transfers, IVMS-101 interoperable.

Detailed memo, every certificate, every regulator letter: /security-compliance.

How fast can I integrate and start verifying users?
  • 60 seconds to a sandbox account at business.didit.me, no credit card.
  • 5 minutes to a working verification through Claude Code, Cursor, or any coding agent via our Model Context Protocol (MCP) server.
  • A weekend to a production-ready integration with signed-webhook verification, retries, and a remediation flow when a user is declined.

Three integration paths, pick whichever fits your stack:

  • Embed natively with our Web, iOS, Android, React Native, or Flutter SDK.
  • Redirect the user to the hosted verification page, zero SDK.
  • Send a link by email, SMS, WhatsApp, or any channel, zero front-end work.

Same dashboard, same billing, same pay-per-success price for all three. Step-by-step guide at docs.didit.me/integration/integration-prompt.

Do I need a fresh check on every user every time?

No. Users who have already passed a Didit-verified session can replay the credential at no cost via Reusable KYC, free forever. Look up the user's prior session_id; if the credential is valid, skip the live gate.

That keeps the friction (and the cost) on traffic you have never seen before. Returning humans pass instantly.

How much does the gate cost?

Two line items:

  • Passive Liveness check: \$0.10 per session
  • Device & IP Analysis pre-screen (optional): \$0.03 per call

500 verifications free every month on every account, most teams sit inside the free tier for weeks. Returning users via Reusable KYC are free forever. No minimums, no annual commitment, no per-seat pricing.

Which surfaces ship this gate?

Anywhere a single bot submission costs the team money or reputation:

  • Marketplace / fintech sign-up forms, to keep disposable accounts out
  • Airdrop / token claims, to keep sybil wallets out
  • Leaderboards / ranking systems, to keep score-pump farms out
  • Referral payouts, to keep self-referral cycles out
  • Comment + review systems, to keep astroturf out
  • Ticket queues, to keep scalper bots out

One workflow, every surface.

Related

相关模块 + 工作流

身份与欺诈基础设施。

一个 API 即可实现 KYC、KYB、交易监控和钱包筛选。5 分钟即可集成。

免费开始联系我们
让 AI 总结此页面