Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels, and rarely exploit semantic clues. For face recognition attacks, existing methods typically generate the ℓp-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models. In this work, instead of performing perturbations on the low-level pixels, we propose to generate attacks through perturbing on the high-level semantics to improve attack transferability. Specifically, a unified flexible framework, Adversarial Attributes (Adv-Attribute), is designed to generate inconspicuous and transferable attacks on face recognition, which crafts the adversarial noise and adds it into different attributes based on the guidance of the difference in face recognition features from the target. Moreover, the importance-aware attribute selection and the multi-objective optimization strategy are introduced to further ensure the balance of stealthiness and attacking strength. Extensive experiments on the FFHQ and CelebA-HQ datasets show that the proposed Adv-Attribute method achieves the state-of-the-art attacking success rates while maintaining better visual effects against recent attack methods.

Privacy issue is a main concern in developing face recognition techniques. Although synthetic face images can partially mitigate potential legal risks while maintaining effective face recognition (FR) performance, FR models trained by face images synthesized by existing generative approaches frequently suffer from performance degradation problems due to the insufficient discriminative quality of these synthesized samples. In this paper, we systematically investigate what contributes to solid face recognition model training, and reveal that face images with certain degree of similarities to their identity centers show great effectiveness in the performance of trained FR models.

Face frontalization refers to the process of synthesizing the frontal view of a face from a given profile. Due to self-occlusion and appearance distortion in the wild, it is extremely challenging to recover faithful results and preserve texture details in a high-resolution. This paper proposes a High Fidelity Pose Invariant Model (HF-PIM) to produce photographic and identity-preserving results.

Neural Information Processing Systems http://nips.cc/

Synthetic face recognition (SFR) aims to generate synthetic face datasets that mimic the distribution of real face data, which allows for training face recognition models in a privacy-preserving manner.

Additionally, real-time inference and generalization to large probe sets remains challenging.

Plus: Meta plans to add face recognition to its smart glasses, Jared Kushner named as part of whistleblower's mysterious national security complaint, and more. The widespread protests in Iran have exposed both Tehran's brutal tactics in the streets, where state authorities have killed thousands of demonstrators since early January, and extreme measures to block access to the global internet. As it has done repeatedly in the past, the Iranian regime cut off the country's residents from the global internet during the latest anti-government uprising. But it also shut down access to the country's intranet, known as the National Information Network, which new research found is becoming a mechanism of constant and pervasive surveillance that may ultimately be the only way Iranians can get online. The last remaining major nuclear weapons treaty between the United States and Russia just expired.

Neural Information Processing Systems http://nips.cc/