按年被提到
20212021 · 5 次2026
AI 安全、伦理与社会影响›算法偏见与监控·arXiv:2109.06467 · cs.CV

Dodging Attack Using Carefully Crafted Natural Makeup

Nitzan Guetta, Asaf Shabtai, Inderjeet Singh, Satoru Momiyama, Yuval Elovici · 2021
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 5 人首次 2021-09-18 · 最近 2022-05-02
5不同的人
2活跃月份
6讨论串
25被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep learning face recognition models are used by state-of-the-art surveillance systems to identify individuals passing through public areas (e.g., airports). Previous studies have demonstrated the use of adversarial machine learning (AML) attacks to successfully evade identification by such systems, both in the digital and physical domains. Attacks in the physical domain, however, require significant manipulation to the human participant's face, which can raise suspicion by human observers (e.g. airport security officers). In this study, we present a novel black-box AML attack which carefully crafts natural makeup, which, when applied on a human participant, prevents the participant from being identified by facial recognition models. We evaluated our proposed attack against the ArcFace face recognition model, with 20 participants in a real-world setup that includes two cameras, different shooting angles, and different lighting conditions. The evaluation results show that in the digital domain, the face recognition system was unable to identify all of the participants, while in the physical domain, the face recognition system was able to identify the participants in only 1.22% of the frames (compared to 47.57% without makeup and 33.73% with random natural makeup), which is below a reasonable threshold of a realistic operational environment.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论azalemeth · 2021-09

“Wow. Figure 1 tells it all -- and highlights how unstable CNNs can be. I can't help but think that in a "real" environment a more traditional facial recognition algo would also be used simultaneously, for example measuring landmark distances, which would be likely to give a high probability of a match.”

Dodging Facial Recognition Using Carefully Crafted Natural Makeup原评论 ↗
被提交为 story · 6 次