Home › Hard problems › Security

Security

Identity when voices and faces can be faked

Solo: possibleOne person can test a narrow slice of it.

the boss, on videodashed: a cloned faceand voice"Pay the supplier now"it's urgent, I'm in a meetingI know that facePayment sentto the fraudsterPasswordsstill typed into fake pages
Seeing and hearing someone is no longer proof: cloned faces and voices pass the "I recognise them" check, and passwords still get phished.

Why it is still open

Video-call and voice-clone fraud beats "I recognise them" checks, and passwords still get phished.

An experiment one person can run in 8 weeks

Design a call-back and passkey check for one payment approval flow and measure how many staged deepfake attempts it stops.

Verdict: Solo: possible

Useful, but staged tests are small.

The solo test behind the verdict

  1. Can it be measured? There is a number that shows you did better, such as an error rate, a catch rate or a cost per answer.
  2. Is it cheap to try? It runs on a laptop, free open models and open data, or under about ₹50,000 of rented GPU time.
  3. Is there a public yardstick? A benchmark or dataset others use, so your result can be compared and believed.
  4. Would a small win get noticed? A lab, a funder or a customer would care about a 10% improvement, not only a full solution.

Four yeses means Solo: strong. Two or three means Solo: possible. Fewer means Follow, don't build.

PreviousPost-quantum migration

All 79 hard problems · Working on this, or know of a result we missed? basant@cleandataengineering.ai