Logo des Repositoriums

Auflistung nach Autor:in "Kakizaki, Kazuya"

1 - 2 von 2
  • Konferenzbeitrag
    On Brightness Agnostic Adversarial Examples Against Face Recognition Systems
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Singh, Inderjeet; Momiyama, Satoru; Kakizaki, Kazuya; Araki, Toshinori
    This paper introduces a novel adversarial example generation method against face recognition systems (FRSs). An adversarial example (AX) is an image with deliberately crafted noise to cause incorrect predictions by a target system. The AXs generated from our method remain robust under real-world brightness changes. Our method performs non-linear brightness transformations while leveraging the concept of curriculum learning during the attack generation procedure. We demonstrate that our method outperforms conventional techniques from comprehensive experimental investigations in the digital and physical world. Furthermore, this method enables practical risk assessment of FRSs against brightness agnostic AXs.
  • Konferenzbeitrag
    Toward Practical Adversarial Attacks on Face Verification Systems
    (BIOSIG 2021 - Proceedings of the 20th International Conference of the Biometrics Special Interest Group, 2021) Kakizaki, Kazuya; Miyagawa, Taiki; Singh, Inderjeet; Sakuma, Jun
    DNN-based face verification systems are vulnerable to adversarial examples. The previous paper's evaluation protocol (scenario), which we called the probe-dependent attack scenario, was unrealistic. We define a more practical attack scenario, the probe-agnostic attack. We empirically show that these attacks are more challenging than probe-dependent ones. We propose a simple and effective method, PAMTAM, to improve the attack success rate for probe-agnostic attacks. We show that PAMTAM successfully improves the attack success rate in a wide variety of experimental settings.