On the advantages of using AI-generated images of filler faces for creating fair lineups

Abstract

Recent advances in artificial intelligence (AI) enable the generation of realistic facial images that can be used in police lineups. The use of AI image generation offers pragmatic advantages in that it allows practitioners to generate filler images directly from the description of the culprit using text-to-image generation, avoids the violation of identity rights of natural persons who are not suspects and eliminates the constraints of being bound to a database with a limited set of photographs. However, the risk exists that using AI-generated filler images provokes more biased selection of the suspect if eyewitnesses are able to distinguish AI-generated filler images from the photograph of the suspect's face. Using a model-based analysis, we compared biased suspect selection directly between lineups with AI-generated filler images and lineups with database-derived filler photographs. The results show that the lineups with AI-generated filler images were perfectly fair and, in fact, led to less biased suspect selection than the lineups with database-derived filler photographs used in previous experiments. These results are encouraging with regard to the potential of AI image generation for constructing fair lineups which should inspire more systematic research on the feasibility of adopting AI technology in forensic settings.

Keywords: AI image generation; Generative artificial intelligence; Lineup fairness; Sequential lineups; Simultaneous lineups.

Figure 1

The 2-HT eyewitness identification model illustrated in the form of processing trees. The rounded rectangles on the left side represent the stimuli that are presented: culprit-present lineups (upper tree) and culprit-absent lineups (lower tree). The rectangles on the right side represent the different categories of responses that can be observed in these lineups. The letters along the branches represent the probabilities of the postulated latent processes (dP: culprit-presence detection; b: biased suspect selection; g: guessing-based selection among the lineup members; dA: culprit-absence detection). The sampling probability of randomly selecting the suspect among the lineup members in case of guessing is given by the reciprocal of n, where n refers to the lineup size.

Figure 2

Estimates of parameter b representing the biased selection of the suspect as a function of filler type (AI-generated images, database-derived photographs) in simultaneous and sequential lineups. The error bars represent standard errors.