Detect, eliminate, and
prevent hiring fraud
with AI.
Flag suspicious profiles upfront with data-driven recruiting fraud detection, so you never waste time interviewing fake candidates.
Trusted by leading companies.
Powered by the industry's largest resume fraud database.
5M+ profiles analyzed
Tofu agents have analyzed over 5 million applicant profiles across top hiring teams, learning the exact patterns that reveal fraud.
Thousands of signals
Tofu enriches candidate profiles against 4B+ internet data points, surfacing discrepancies across employment history, contact information, credentials, IP address and more — profiles are distilled into thousands of signals and analyzed to determine risk.
92%–97%+ accuracy
Tofu's purpose-built models detect candidate fraud with 92%–97% accuracy and are reviewed weekly against confirmed, labeled cases of legitimate and suspicious candidates.
Always-on detection
Tofu runs automatically the moment a candidate hits your ATS, flagging fake applications before they ever reach the first interview.
Stop fraud before it costs you.
Tofu candidate fraud detection agents analyzes thousands of signals to detect fraud patterns and filter fake applicants when they reach your ATS — keeping your pipeline secure through advanced recruitment fraud detection.
Detect Anywhere
Detect fraud at application review — or anywhere you want.
Run Tofu at the top of your funnel to stop bad actors before they hit your pipeline, or anywhere further down the interview process — pre-interview, pre-offer, or across active stages. Your team decides where fraud detection is turned on.
Validate & Verify
Candidate identity verification that focuses your team on real applicants.
Tofu's candidate identity verification leverages dozens of open and closed-source databases to validate candidates across 4 billion people data points — a faster, smarter background check alternative. Flag suspicious profiles in seconds with high accuracy, so you only spend time reviewing genuine candidates instead of wasting hours on fake applications.
Screen & Reject at Scale
Screen and reject fraud at scale.
Tofu automatically labels every applicant so you can reject suspicious or fraudulent profiles in bulk. Stop reviewing fake candidates one by one and clear them out fast — at whatever volume your team is hiring.
Recruiting & Security
Designed for recruiting and security teams.
Send your own signals to Tofu to ingest into our fraud detection models. Our system adapts to the unique fraud patterns your team is seeing — built to fit both recruiting and security workflows.
Stop fraud before it costs you.
Tofu candidate fraud detection agents analyzes thousands of signals to detect fraud patterns and filter fake applicants when they reach your ATS — keeping your pipeline secure through advanced recruitment fraud detection.
Detect fraud at application review — or anywhere you want.
Run Tofu at the top of your funnel to stop bad actors before they hit your pipeline, or anywhere further down the interview process — pre-interview, pre-offer, or across active stages. Your team decides where fraud detection is turned on.
Applicants remaining
482
Applicants remaining
71
Applicants remaining
10
Applicants remaining
4
ATS fraud detection built right into your workflow.
Applicant tracking fraud thrives when bad actors exploit gaps between your ATS and verification workflows. Tofu eliminates those gaps. Fraud Agents label fraudulent candidates directly in your ATS and adds verification details to application profile notes. Everything stays in your ATS. Including you.
The cost of one bad hire.
Hiring someone from a sanctioned country like North Korea — even unknowingly — is a federal violation. Every paycheck made is considered a separate offense.
Calculate your exposure01
Strict Liability
OFAC doesn't care if you didn't know. Intent is irrelevant — if a sanctioned individual is on your payroll, you're liable from day one.
02
Violations Stack
One contractor, six months, bi-weekly pay. That's 13 violations at $356K each — $4.6M in civil penalties before criminal charges even enter the picture.
03
No Screening, No Defense
The single biggest factor OFAC weighs when setting penalties is whether you had a screening program. No documentation means no leverage when enforcement shows up.
The cost of one bad hire.
The Office of Foreign Assets Control is a division of the U.S. Treasury that enforces economic and trade sanctions against foreign adversaries. North Korea is a comprehensively sanctioned country. Any financial transaction with a North Korean national — like salary to an employee, is a federal sanctions violation.
Calculate your exposure$0
Max civil fine per violation
0
The value of the transaction
$0M+
Criminal fine per violation
0
Each paycheck = a separate violation
Strict Liability
OFAC doesn't care if you didn't know. Intent is irrelevant — if a sanctioned individual is on your payroll, you're liable from day one.
Violations Stack
One contractor, six months, bi-weekly pay. That's 13 violations at $356K each — $4.6M in civil penalties before criminal charges even enter the picture.
No Screening, No Defense
The single biggest factor OFAC weighs when setting penalties is whether you had a screening program. No documentation means no leverage when enforcement shows up.
Types of hiring fraud tofu detects.
01
State-sponsored IT worker fraud
Foreign threat actors leverage stolen identities, VPNs, and proxies to access remote technical roles. North Korean IT worker fraud rings — identified by the FBI, OFAC, and other agencies — represent a documented and growing concern.
02
Synthetic identity fraud
Fraudsters combine legitimate and fabricated information — authentic employment records, valid credentials, and false contact information — to establish synthetic identities that circumvent standard screening.
03
Location spoofing
Fraudulent applicants mask their geographic location using VPNs, proxies, and GPS tools to conceal applications from sanctioned countries or misrepresent remote work eligibility.
04
Deepfake interview fraud
Bad actors use AI-generated video and audio to impersonate candidates during live interviews or conceal their true identity. Tofu's detection system uses behavioral and identity markers to identify fraudulent candidates.
05
Proxy interviewer fraud
Candidates hire stand-ins to complete technical interviews on their behalf, then a different candidate shows up to the job on day one. Tofu detects identity mismatches and behavioral indicators across the interview process.
Types of hiring fraud tofu detects.
More from tofu.
Insights, research, and updates on applicant fraud.
IT Worker Fraud Has an Identity Problem
We pulled every case our resume fraud detection tool flagged as a possible impersonation. What we found — deepfakes, stolen LinkedIn photos, and real-time face-swapping software — was worse than we expected.
Resume Fraud Detection Needs A Human Score
We've spent two years building one of the largest fraudulent candidate datasets in the industry — over 5M applicants, billions of data points. Here's the signal that surprised us most.
tofu. + Gem: Applicant Fraud Detection in Gem's Product Suite
Recruiting has quietly entered a crisis. The combination of generative AI and remote work has made it incredibly easy for bad actors to flood hiring pipelines with fake identities, deepfakes, and AI-generated candidates.