PRIVACY AWARE people who wear spectacles should immediately dump their plain frames and pick up a pair that Dame Edna Everage would probably file under too tacky.
Yeah, it's probably going to have to be a compromise to your identity, and it will be very 'in your face', but it's probably worth it.
We are not just making this up. A research paper has been published that is presumably the talk of artisan opticians everywhere. It also makes good reading for privacy people.
The paper, Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition (PDF), was presented at the 2016 Computer and Communications Security conference by the great minds from Carnegie Mellon University.
"In this paper, we focus on facial biometric systems, which are widely used in surveillance and access control," said the paper.
"We define and investigate a novel class of attacks that are physically realisable and inconspicuous, and allow an attacker to evade recognition or impersonate another individual.
"We develop a systematic method to automatically generate such attacks, which are realised through printing a pair of eyeglass frames.
"When worn by the attacker whose image is supplied to a state-of-the-art face recognition algorithm, the eyeglasses allow them to evade being recognised or to impersonate another individual."
The report isn't a guide for the privacy aware but a scare paper for people who want to avoid wasting a lot of money on camera surveillance equipment.
"In this paper, we explore the extent to which facial biometric systems are vulnerable to attacks. These systems are widely used for various sensitive purposes, including surveillance and access control. Thus, attackers who mislead them can cause severe ramifications," the paper said.
"Such attacks help the perpetrators (whether malicious or benign) achieve plausible deniability; e.g. a person seeking merely to protect their privacy against aggressive use of face recognition by merchants will plausibly be able to claim that any failure of a machine learning algorithm to recognise them is due to error or chance rather than deliberate subterfuge."
The meat of this, for us, is that the researchers found that wearing a ridiculous pair of spectacles is enough to confuse a camera designed to identify people. µ
Firms fight Fortress over flimsy feuds
Hashes to hashes
Team Green cranks the Super GPU machine