Find the alts. And whose they are.
Ban evaders, multi-accounters and fraud rings stay invisible until you can connect identities. Pro links devices and accounts with confidence-scored evidence, and answers in your own user IDs, one hop or two, not in anomaly scores.
EU-hosted. Verdicts in milliseconds.
One device, four accounts, two hops. The ring stops being invisible.
Already in production
Publishing platforms, fintech and national charities across Europe already run TrustSig on their forms.
PublitPrint-on-demand and digital book distribution for publishers.Publishing · Sweden
LEI SystemOfficial Legal Entity Identifier registration agent.Fintech · Estonia
Disability Sport WalesNational charity for inclusive and disability sport.Charity · Wales
Links are earned, not guessed.
Every edge in the graph carries its evidence and a confidence score. Weak signals stay weak, and it takes corroboration to convict, which is exactly why office Wi-Fi doesn't create false rings. A few of the signals that build a link:
One hop finds the alt. Two hops find the ring.
Start from any suspicious account and expand: first the accounts sharing its devices, then the wider component connected through them. Promo-abuse rings and ban-evasion clusters surface as one structure instead of twenty isolated incidents.
Surface the ring behind one account.
Book a demoBans that actually stick.
The ban-evasion loop only works because the new account starts from zero. With device and network memory, it doesn't.
The loop ends where the hardware repeats.
Make bans that actually stick.
Book a demoNames, not noise.
Most tools hand you an anomaly score and wish you luck. Pro returns the related accounts in your own user IDs with the evidence per link, and your team can confirm or reject links to sharpen future calls.
{ "entity": "ent_a91f", "alts": [ { "user_id": "u_9907", "confidence": 94, "evidence": ["shared_device", "account_overlap"] }, { "user_id": "u_1003", "confidence": 71, "evidence": ["ip_time_proximity", "shared_device"] } ]}Get the alts back in your own user IDs.
Book a demoOne signal layer. Every abuse pattern.
Each detection engine reads the same account, device and network memory – turn on one, the rest are a toggle away.
Alt detection, answered
It links accounts on evidence like a shared device fingerprint, the same IP within a tight time window, and direct account overlap on shared entities, among other signals. Each link carries a confidence score built from how many independent evidence kinds support it.
Most tools tell you an account 'looks suspicious'. Pro returns the actual related accounts — in your own user IDs — with the confidence and the evidence behind each link. You see u_4821 is an alt of u_9907, not just an anomaly score.
Yes. Link expansion works one hop (this device's other accounts) and two hops (the wider connected ring), so a ban-evasion cluster or promo-abuse ring surfaces as one connected component instead of isolated incidents.
When a banned user signs up again, the new account links back through the same device or network within the first sessions. Your enforcement carries over to the new identity instead of resetting to zero.
Shared-IP evidence alone produces low confidence precisely for this reason — it takes corroborating evidence like a shared device or account overlap to reach high confidence. You also see the evidence per link, so borderline cases are inspectable, and you can confirm or reject links to teach the system.
Surface the alt accounts behind the abuse.
Tell us what you are trying to protect and why now. We will reply by email to set up access for your team.
- EU-hosted, GDPR-native
- No CAPTCHAs, no friction for your users
- Verdicts in milliseconds