상세 보기
변형과 적대적 학습에 강건한 얼굴 사진 보호 기법 연구
- 오병훈;
- 이재우
초록
Publicly shared face photos can be collected and used to train facial recognition models without the owner's consent. Unlearnable examples counter this by adding imperceptible noise to photos before sharing. In practice, however, collected photos undergo transforms before training; face recognition in particular crops the face and resizes it. Moreover, the attacker may adopt adversarial training to erase the effect of the noise. We show that existing unlearnable examples designed to withstand adversarial training lose their protection after this transform alone. We then propose SafeFace, which confines the noise to the face region, generates it through a differentiable model of the attacker's transform, and gradually increases the adversarial perturbation budget assumed during generation. On 50 identities, SafeFace is the only method among the five compared that withstands both conditions, suppressing the attacker to 1.8% under the transform and 12.0% under adversarial training , where prior methods allow 33.2-42.2%
키워드
- 제목
- 변형과 적대적 학습에 강건한 얼굴 사진 보호 기법 연구
- 제목 (타언어)
- A Study on Face Photo Protection Robust to Transforms and Adversarial Training
- 저자
- 오병훈; 이재우
- 발행일
- 2026-09
- 유형
- Y
- 호
- 88
- 페이지
- 51 ~ 70
- 언어
- KOR
- 출판사
- 한국보안관리학회
- 발행국가
- 대한민국
- 분량
- 20 페이지
- ISSN
- E 2714-0644
P 2671-4299