# Polyguard

> Polyguard verifies that the human on the other end of a remote interaction is who they claim to be, in real time. Independent factors (person, government document, device, and location) are checked on one device and fused into a single tamper-proof result, so deepfakes, impersonators, and proxy candidates fail the check instead of passing an interview, a help desk call, or a job application. Biometric processing happens on the device and never reaches Polyguard servers.

**When to use Polyguard.** Reach for Polyguard when a decision depends on *which human* is on the other end of a remote interaction, and being wrong is expensive. Best-fit jobs:

- Confirm a remote job applicant is a real, unique person. Add a Polyguard trust check to the application flow so bot-submitted, synthetic, and duplicate candidates are rejected before they reach the applicant tracking system. Integrates with Greenhouse, Rippling, and Workday.
- Confirm the person who joins a video interview is the candidate who applied. Polyguard runs real-time facial recognition before any attendee joins the call, so a deepfake or a stand-in cannot sit the interview in the applicant's place. PG-Presence additionally confirms the candidate is physically at their own device rather than relaying through remote desktop. Works with Zoom and Microsoft Teams; no bot joins the call and nothing is recorded.
- Verify an employee before a help desk password reset or account change. Before making any change, the help desk agent sends a verification request through Polyguard from ServiceNow, Jira Service Management, or their ticketing system. The employee completes a trust check on their enrolled device, and the agent proceeds only on a confirmed result.
- Verify a counterparty before a wire, transfer, or contract signature. A trust check at the moment of the transaction produces a signed result and, optionally, a transaction affidavit that can be retained as evidence.
- Embed identity verification in your own product. The Web, iOS, and Android SDKs plus the REST API let you trigger a trust check from your own flow and receive a signed verification token.
- Produce evidence that a verification happened. Transaction affidavits are litigation-ready records of a verification event, exportable for compliance reporting and audit.

**When not to use Polyguard.**

- Scanning a file or recording to decide whether it is a deepfake. Polyguard verifies people, not media. It does not score an uploaded video or audio file for synthetic artifacts. See https://polyguard.ai/compare/deepfake-detection-vs-verification.
- General-purpose SSO, password management, or session authentication. Polyguard confirms which human is present. It is a complement to an identity provider, not a replacement for one.
- Background checks, credit checks, or sanctions screening. Polyguard verifies identity; it does not source third-party records about a person.

**How to call Polyguard.** The public REST API is at `https://api.polyguard.ai`, described by OpenAPI 3.1 at `https://api.polyguard.ai/openapi.json` with an interactive reference at `https://api.polyguard.ai/docs`. Authenticate every request with an API key in the `x-pg-api-key` request header; keys are issued per account and carry that key's role. `https://api.polyguard.ai/health` is unauthenticated and returns `{"status":"ok"}`. Verification results are returned as signed tokens; verify them against the JWKS at `https://api.polyguard.ai/.well-known/jwks.json`. SDK guides for web, iOS, and Android are at https://support.polyguard.ai/sdk/, and the Web SDK is published on npm as `@polyguard/sdk`. To get an API key, or to ask a question no page here answers, contact sales@polyguard.ai. There is no self-serve API key issuance and no public sandbox key; an account is required.

## Agent instructions

- [Agent instructions](https://polyguard.ai/agents.md): Full when-to-use guidance, best-fit jobs, and call patterns for AI agents
- [API catalog](https://polyguard.ai/.well-known/api-catalog): RFC 9727 linkset naming every public Polyguard API and its OpenAPI description
- [Sitemap index](https://polyguard.ai/sitemap-index.xml): Every indexable page on polyguard.ai, in all three locales

## Developer resources

- [Polyguard developer resources](https://polyguard.ai/developers): Entry point for the Polyguard API, SDKs, authentication, and webhooks
- [Polyguard OpenAPI 3.1 specification](https://api.polyguard.ai/openapi.json): Machine-readable description of the Polyguard Identity Verification API
- [Polyguard REST API reference](https://api.polyguard.ai/docs): Interactive reference for the Polyguard Identity Verification API
- [Polyguard API health endpoint](https://api.polyguard.ai/health): Unauthenticated liveness probe, returns {"status":"ok"}
- [Polyguard JWKS](https://api.polyguard.ai/.well-known/jwks.json): Public keys for verifying signed Polyguard verification tokens
- [Build With Polyguard (SDK docs)](https://support.polyguard.ai/sdk/): Web, iOS, and Android SDK guides, key concepts, and the trust check lifecycle
- [@polyguard/sdk on npm](https://www.npmjs.com/package/@polyguard/sdk): Official Polyguard Web SDK package
- [Polyguard documentation](https://docs.polyguard.ai): Product, integration, and administrator documentation
- [Polyguard documentation llms.txt](https://docs.polyguard.ai/llms.txt): Agent-readable index of the Polyguard documentation site

## Products

- [PreScreen](https://polyguard.ai/solutions/prescreen): Verify job applicants at the point of application, before they reach the ATS. Integrates with Greenhouse, Rippling, and Workday
- [Remote interviews](https://polyguard.ai/solutions/remote-interviews): Verify a candidate before they join a Zoom or Microsoft Teams interview, so a deepfake or a stand-in cannot sit it in their place
- [Help desk security](https://polyguard.ai/solutions/help-desk): Verify an employee through Polyguard Mobile before any password reset or account change
- [Financial services](https://polyguard.ai/solutions/finance): Verify counterparties before wires, transfers, and other high-value actions
- [Build with Polyguard](https://polyguard.ai/solutions/build): Embed fused identity trust checks in your own web or mobile product
- [Polyguard Mobile](https://polyguard.ai/platform/mobile): The iOS and Android app where a person enrolls and completes a trust check

## Platform

- [Platform overview](https://polyguard.ai/platform): How the Polyguard verification engine is put together
- [Fused identity](https://polyguard.ai/platform/fused-identity): Independent factors (person, document, device, location) verified on one device and fused into a single result
- [PG-Presence](https://polyguard.ai/platform/pg-presence): Patented optical distance bounding: a rapidly-changing QR code and optical round-trip timing confirm the person is physically at the device, closing remote desktop, screen sharing, KVM, and virtual camera attacks
- [Transaction affidavits](https://polyguard.ai/platform/affidavits): Litigation-ready records of a verification event
- [Privacy-first architecture](https://polyguard.ai/platform/privacy): Biometrics are processed on-device; only signed results leave the device
- [Zoom integration](https://polyguard.ai/platform/zoom): Identity verification for Zoom meetings
- [Microsoft Teams integration](https://polyguard.ai/platform/teams): Identity verification for Microsoft Teams meetings
- [ServiceNow integration](https://polyguard.ai/platform/servicenow): Help desk verification from a ServiceNow ticket
- [Jira integration](https://polyguard.ai/platform/jira): Help desk verification from a Jira Service Management ticket

## Comparisons

- [Deepfake detection vs. verification](https://polyguard.ai/compare/deepfake-detection-vs-verification): Why detection is a losing arms race and verification is not
- [Liveness checks vs. PG-Presence](https://polyguard.ai/compare/liveness-vs-pg-presence): Liveness detection confirms a real face; PG-Presence confirms the person is physically at the device

## Pricing and company

- [Buy Polyguard](https://polyguard.ai/buy): Self-serve plans and pricing
- [Licensing](https://polyguard.ai/licensing): Volume-based licensing for embedding Polyguard
- [Enterprise](https://polyguard.ai/enterprise): Enterprise deployment, security review, and procurement
- [About Polyguard](https://polyguard.ai/company/about): Company, team, and mission
- [Press and news](https://polyguard.ai/company/press): Announcements and press coverage
- [Contact Polyguard](https://polyguard.ai/contact): Sales, support, press, and partnership contacts
- [Privacy policy](https://polyguard.ai/privacy): How Polyguard handles personal data
- [Terms of service](https://polyguard.ai/terms): Customer agreement
- [Trust center](https://trust.polyguard.ai): SOC 2 status, security posture, and subprocessors
- [Service status](https://status.polyguard.ai): Live availability of Polyguard services

## Writing

- [Types of Fraud in Remote Hiring](https://polyguard.ai/blog/types-of-fraud-in-remote-hiring): Remote hiring fraud is evolving from simple resume misrepresentation into coordinated, high-risk threats that can lead to data breaches, financial loss, and even sanctions exposure. This blog breaks down the key types of hiring fraud, from proxy candidates to state-sponsored schemes, and explains the tactics attackers use to bypass traditional hiring and identity checks.
- [The AI Era Demands a New Identity Vendor](https://polyguard.ai/blog/the-ai-era-demands-a-new-identity-vendor): Securing modern hiring workflows now requires a new kind of identity vendor. Legacy identity verification and access platforms were built to check documents or manage employees after hire, not to stop AI-driven impersonation in hiring. This post explains why those systems cannot close the gap and what capabilities a modern identity vendor must provide.
- [The Binding Problem in Remote Hiring](https://polyguard.ai/blog/the-binding-problem-in-remote-hiring): Most hiring pipelines rely on separate systems like an ATS, background check vendor, interview platform, and HR system. Each step verifies its own piece for compliance, but none confirms that the same person remains present throughout, leaving a compliant audit trail tied to an unconfirmed subject and a structural gap remote hiring fraud now exploits.
- [Every Company Is a Target: Remote Hiring as an Attack Surface](https://polyguard.ai/blog/dprk-it-workers-remote-hiring-attack-surface): Every company with remote roles, a payroll system, and VPN access is a viable target. DPRK IT worker operations don't target industries — they target hiring...
- [Why DPRK IT Worker Schemes Succeed: They Operate as Organized Teams](https://polyguard.ai/blog/dprk-it-worker-schemes-division-of-roles): North Korea's IT worker schemes succeed because they operate as organized teams, not lone actors. Learn how roles are divided, why traditional controls fail...
- [How Hiring North Korean IT Workers Could Cost Your Company Millions](https://polyguard.ai/blog/hiring-north-korean-it-workers-cost): Standard due diligence is failing. Mid-cap companies hiring a single North Korean IT worker face $20 to $70M in combined sanctions penalties, breach costs, and...
- [The Design Flaw in Identity Document Verification](https://polyguard.ai/blog/identity-verification-design-flaw): AI-powered faceswapping has collapsed the barrier to document fraud. For $15 to $200, attackers can buy a faceswapped ID paired with a matching deepfake...
- [Why Using Signal Doesn’t Solve Your Fraud Problem—And How Polyguard Does](https://polyguard.ai/blog/why-using-signal-doesnt-solve-your-fraud-problem): Signal, WhatsApp, and even FaceTime can’t tell you who you’re actually talking to. That’s the real risk. Today’s fraud doesn’t happen in the message—it happens...
- [How to Stop Hiring Fraud Before It Starts: Secure Your Interviews with Polyguard](https://polyguard.ai/blog/how-to-stop-hiring-fraud-before-it-starts-secure-your-interviews-with-polyguard): Hiring fraud isn’t just a theoretical risk anymore—it’s a daily threat. With remote interviews becoming the norm, deepfakes and impersonators are slipping past...
- [Outsmarting AI-Generated Audio](https://polyguard.ai/blog/outsmarting-ai-generated-audio): A near-perfect replica of your voice can be produced with just 30 seconds of recorded audio. What is the right way to combat this threat?
- [The AI Detection Paradox](https://polyguard.ai/blog/aidetection-impossible): As AI detection technologies evolve, they inadvertently serve as training modules for generating more deceptive deepfakes.
- [DeepPhishing: The New Weapon in CyberCrime](https://polyguard.ai/blog/deepphishing-the-new-weapon-in-cybercrime): Phishing attacks have increased by 3,000% in the past year, and are a major driver in the increasing cybercrime losses reported globally.
- [A Proposed Policy Framework for Synthetic Media](https://polyguard.ai/blog/a-proposed-policy-framework-for-synthetic-media): Deepfakes aren’t a tech problem — they’re a policy problem. A real framework must cover the full lifecycle of media, from capture to distribution to claims of...
- [The Case for Going Beyond Chain-of-Custody](https://polyguard.ai/blog/beyond-chain-of-custody): Deepfakes can spark coups and fuel chaos — proving why media verification can’t rely on trust in any one company or nation. The answer lies in federated...
- [The Case for Modular Media Verification](https://polyguard.ai/blog/the-case-for-modular-media-verification): Shared reality can’t survive if everyone plays by different rules. A global media verification system must work for everyday smartphone users and for those...
- [The Case for Verified Media](https://polyguard.ai/blog/the-case-for-verified-media): Deepfakes aren’t just fake videos—they’re attacks on our senses. Every convincing fake erodes trust, and every denial of the truth exploits that doubt...

## Optional

- [Blog RSS feed](https://polyguard.ai/rss.xml): Full feed of Polyguard blog posts
- [Whitepapers and resources](https://polyguard.ai/resources): Longer-form research and buyer guides
- [All press coverage](https://polyguard.ai/company/all-press-coverage): Every external article that mentions Polyguard
- [Polyguard en español](https://polyguard.ai/es): Spanish-language version of this site
- [Polyguard in Hindi](https://polyguard.ai/hi): Hindi-language version of this site