activity
20202026
most citedAre GAN-based Morphs Threatening Face Recognition?

53 citations · 82 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2026

Benchmarking the Explanatory Quality of Open-Weight Vision-Language Models in Face Recognition

Laurent Colbois, Sébastien Marcel

Vision-Language Models (VLMs) have recently been proposed as promising tools for face recognition, as they can produce natural language explanations alongside similarity scores. Th…

cs.CV2024★ 4 cited

Evaluating the Effectiveness of Attack-Agnostic Features for Morphing Attack Detection

Laurent Colbois, Sébastien Marcel

Morphing attacks have diversified significantly over the past years, with new methods based on generative adversarial networks (GANs) and diffusion models posing substantial threat…

cs.CV2024★ 5 cited

Approximating Optimal Morphing Attacks using Template Inversion

Laurent Colbois, Hatef Otroshi Shahreza, Sébastien Marcel

Recent works have demonstrated the feasibility of inverting face recognition systems, enabling to recover convincing face images using only their embeddings. We leverage such templ…

cs.CV2022★ 11 cited

On the detection of morphing attacks generated by GANs

Laurent Colbois, Sébastien Marcel

Recent works have demonstrated the feasibility of GAN-based morphing attacks that reach similar success rates as more traditional landmark-based methods. This new type of "deep" mo…

cs.CV2022★ 53 cited

Are GAN-based Morphs Threatening Face Recognition?

Eklavya Sarkar, Pavel Korshunov, Laurent Colbois +1

Morphing attacks are a threat to biometric systems where the biometric reference in an identity document can be altered. This form of attack presents an important issue in applicat…

cs.CV2021★ 1 cited

On the use of automatically generated synthetic image datasets for benchmarking face recognition

Laurent Colbois, Tiago de Freitas Pereira, Sébastien Marcel

The availability of large-scale face datasets has been key in the progress of face recognition. However, due to licensing issues or copyright infringement, some datasets are not av…