Targeted biometric impersonation

Abstract

When applying biometric algorithms to forensic verification, false acceptance and false rejection can mean a failure to iden tify a criminal, or worse, lead to the prosecution of individuals for crimes they did not commit. It is therefore critical that bio metric evaluations be performed as accurately as possible to determine their legitimacy as a forensic tool. This paper ar gues that, for forensic verification scenarios, traditional per formance measures are insufficiently accurate. This inaccu racy occurs because existing verification evaluations implic itly assume that an imposter claiming a false identity would claim a random identity rather than consciously selecting a target to impersonate. In addition to describing this new vul nerability, the paper describes a novel Targeted..FAR metric that combines the traditional False Acceptance Rate (FAR) measure with a term that indicates how performance degrades with the number of potential targets. The paper includes an evaluation of the effects of targeted impersonation on an ex isting academic face verification system. This evaluation re veals that even with a relatively small number of targets false acceptance rates can increase significantly, making the anal ysed biometric systems unreliable.

Measuring and mitigating targeted biometric impersonation

“…A recent conference paper has shown that this attack is also effective against face verification [4]. This paper is an expansion of that publication.…”

“…This paper is concerned with two situations in forensics that significantly increase the chances of false positives being reported. One is targeted biometric impersonation [4] and the other is as a result of individuals being preselected for assessment. Targeted biometric impersonation involves locating an innocent person in the verification system with a similar biometric signature and then fraudulently assuming that identity to spoof a verification check.…”

“…Targeted impersonation was first introduced as a method of spoofing gait verification systems [5]. A recent conference paper has shown that this attack is also effective against face verification [4]. This paper is an expansion of that publication.…”

Targeted impersonation as a tool for the detection of biometric system vulnerabilities

“…The effect of targeted attacks has been studied for both face [3] and gait verification systems [9]. In the case of gait verification the attack was used with another impersonation method to create the first successful spoofing attempt against that biometric.…”