Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation
This work addresses privacy concerns for users of social media and face recognition systems by enhancing the generalization of invisible facial cloaks, though it appears incremental as it builds on existing class-universal methods.
The authors tackled the problem of optimizing adversarial privacy cloaks for facial images by addressing local optima and gradient elimination issues, proposing Gradient Accumulation to improve stability and reduce quantization, achieving high performance on the Privacy-Commons dataset against black-box models.
The blooming of social media and face recognition (FR) systems has increased people's concern about privacy and security. A new type of adversarial privacy cloak (class-universal) can be applied to all the images of regular users, to prevent malicious FR systems from acquiring their identity information. In this work, we discover the optimization dilemma in the existing methods -- the local optima problem in large-batch optimization and the gradient information elimination problem in small-batch optimization. To solve these problems, we propose Gradient Accumulation (GA) to aggregate multiple small-batch gradients into a one-step iterative gradient to enhance the gradient stability and reduce the usage of quantization operations. Experiments show that our proposed method achieves high performance on the Privacy-Commons dataset against black-box face recognition models.