Health & Education
Remote assessment moved the exam hall onto a laptop, and the question of who is sitting the paper became a question about a video window. FaceOff confirms the candidate throughout the assessment and gives the qualification something an employer can verify afterwards, without turning an exam into an interrogation
Overview
Protect exam integrity in remote assessment and confirm the identity of the person sitting the paper or presenting a qualification.
An exam has always rested on a quiet assumption: that the person who wrote the paper is the person whose name is on it. In a hall, an invigilator settled that simply by being present. Remote assessment removed the invigilator and left a video window in their place.
A window is easy to work around. A candidate can be coached from just outside the frame, replaced part way through by somebody who knows the subject better, or helped by material on a second screen the camera never sees. Later the certificate itself becomes the target, because a qualification is trusted by employers and universities who have no practical way to check it.
The checks below confirm the candidate through the assessment rather than only at the start, and give a qualification something anybody can verify. Every finding goes to a member of staff to review, because an academic decision belongs to your institution and never to software.
What you deploy
These are the products universities, examination boards and training providers deploy most often, following an assessment from the moment a candidate signs in to the point where the qualification is presented to somebody else.
Autonomous voice interviewer with trimodal audio, visual and linguistic forensics.
ExploreLive face recognition across your camera network, matched against your watch-lists.
ExploreKey capabilities
What this sector asks for most often. Each one runs at the moment a decision is being made, and each returns a result a reviewer can explain to somebody else.
Confirmation continues through the assessment rather than stopping at sign in, so a paper that changes hands part way through is surfaced while the session is still open instead of being inherited from a check that passed an hour earlier.
Somebody presenting a photograph, a screen capture or video of the candidate filmed earlier should not be accepted as that candidate. The check is built to resist material prepared in advance rather than treating any face in front of a camera as a person who is really there.
Images and video that appear on screen during an online assessment or an admissions interview can be checked while they are still open, so a document or a clip offered as evidence is examined at the moment it is offered rather than long afterwards.
A certificate carries a code confirming it is genuine and has not been altered, and it can be checked without an internet connection. A copy of the code does not become a trusted code, which is the difference between a verifiable credential and a well printed one.
A candidate can be interviewed by voice, with the conversation read across what was said, how it was said and how the candidate appeared while saying it. That makes a spoken component workable for a large cohort spread across time zones, where arranging a panel for every candidate is not.
Nothing here accuses a candidate of anything. Each finding reaches a member of staff with the reasoning attached, and what follows is your own academic process, which is also what makes an appeal answerable months after the exam.
Where it is used
Every entry names a product on this site and describes it the way its own page does.
BehaviorBioAuth checks identity from behaviour and keeps checking, so a candidate who is replaced part way through is caught.
BehaviourLens AI holds a spoken conversation with a candidate and reads voice, face and words together.
DeepBrowserGuard checks images and video people meet online while they are on screen.
QuantumSafe QR gives a credential a code that confirms it is genuine and has not been altered.
Common questions
Yes. BehaviorBioAuth keeps checking through the session rather than only at sign in, so a change of person part way through is surfaced instead of inherited from the first check. The finding goes to a member of staff to review rather than ending the exam automatically.
BehaviorBioAuth stores no biometric templates. An institution can confirm a candidate without becoming the permanent holder of a biometric record of every student it has ever assessed.
No. It raises something for a person to review, with the reasoning attached. The academic decision, any interview that follows and any appeal remain entirely your institution's own process.
The check is built to resist material captured in advance, so a photograph, a screen capture or video recorded earlier should not pass as a candidate who is present and answering now.
Yes. BehaviourLens AI holds a spoken conversation with a candidate and reads voice, face and words together, which makes a spoken assessment practical at a scale where arranging a human panel for every applicant is not.
Yes. QuantumSafe QR gives a credential a code confirming it is genuine and unaltered, and it can be checked offline by an employer or another institution without contacting your office. It is designed for credentials that have to stay trustworthy for a very long time.
The checks are designed to run alongside the assessment rather than adding tasks a genuine candidate has to complete, and DeepBrowserGuard reaches a cohort as a browser extension. Exactly how that fits your own assessment platform is worth walking through on a demo rather than stated as a rule here.
The checks are built to run continuously rather than case by case, and each returns a graded finding. That lets invigilator attention go to the small number of sessions that raised something instead of being spread evenly and thinly across every candidate.
Yes. Any method of detection can be mistaken in either direction, human judgement included. A finding is an evidence based reason to look at a session, not a conclusion about a student, which is why the evidence comes with it and why the decision stays with your academic staff.
Bring your own footage. We will run it through the Adaptive Cognito Engine and walk you through the findings.
