RiDDLE: Reversible and Diversified De-identification with Latent
Encryptor
- URL: http://arxiv.org/abs/2303.05171v3
- Date: Sun, 23 Apr 2023 06:52:20 GMT
- Title: RiDDLE: Reversible and Diversified De-identification with Latent
Encryptor
- Authors: Dongze Li, Wei Wang, Kang Zhao, Jing Dong and Tieniu Tan
- Abstract summary: This work presents RiDDLE, short for Reversible and Diversified De-identification with Latent Encryptor.
Built upon a pre-learned StyleGAN2 generator, RiDDLE manages to encrypt and decrypt the facial identity within the latent space.
- Score: 57.66174700276893
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work presents RiDDLE, short for Reversible and Diversified
De-identification with Latent Encryptor, to protect the identity information of
people from being misused. Built upon a pre-learned StyleGAN2 generator, RiDDLE
manages to encrypt and decrypt the facial identity within the latent space. The
design of RiDDLE has three appealing properties. First, the encryption process
is cipher-guided and hence allows diverse anonymization using different
passwords. Second, the true identity can only be decrypted with the correct
password, otherwise the system will produce another de-identified face to
maintain the privacy. Third, both encryption and decryption share an efficient
implementation, benefiting from a carefully tailored lightweight encryptor.
Comparisons with existing alternatives confirm that our approach accomplishes
the de-identification task with better quality, higher diversity, and stronger
reversibility. We further demonstrate the effectiveness of RiDDLE in
anonymizing videos. Code and models will be made publicly available.
Related papers
- CodeChameleon: Personalized Encryption Framework for Jailbreaking Large
Language Models [49.60006012946767]
We propose CodeChameleon, a novel jailbreak framework based on personalized encryption tactics.
We conduct extensive experiments on 7 Large Language Models, achieving state-of-the-art average Attack Success Rate (ASR)
Remarkably, our method achieves an 86.6% ASR on GPT-4-1106.
arXiv Detail & Related papers (2024-02-26T16:35:59Z) - PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via
Secure Flow [69.78820726573935]
We name it PRO-Face S, short for Privacy-preserving Reversible Obfuscation of Face images via Secure flow-based model.
In the framework, an Invertible Neural Network (INN) is utilized to process the input image along with its pre-obfuscated form, and generate the privacy protected image that visually approximates to the pre-obfuscated one.
arXiv Detail & Related papers (2023-07-18T10:55:54Z) - Publicly-Verifiable Deletion via Target-Collapsing Functions [81.13800728941818]
We show that targetcollapsing enables publiclyverifiable deletion (PVD)
We build on this framework to obtain a variety of primitives supporting publiclyverifiable deletion from weak cryptographic assumptions.
arXiv Detail & Related papers (2023-03-15T15:00:20Z) - Generative Model-Based Attack on Learnable Image Encryption for
Privacy-Preserving Deep Learning [14.505867475659276]
We propose a novel generative model-based attack on learnable image encryption methods proposed for privacy-preserving deep learning.
We use two state-of-the-art generative models: a StyleGAN-based model and latent diffusion-based one.
Results show that images reconstructed by the proposed method have perceptual similarities to plain images.
arXiv Detail & Related papers (2023-03-09T05:00:17Z) - Revocable Cryptography from Learning with Errors [61.470151825577034]
We build on the no-cloning principle of quantum mechanics and design cryptographic schemes with key-revocation capabilities.
We consider schemes where secret keys are represented as quantum states with the guarantee that, once the secret key is successfully revoked from a user, they no longer have the ability to perform the same functionality as before.
arXiv Detail & Related papers (2023-02-28T18:58:11Z) - Device-independent uncloneable encryption [0.0]
We introduce a variant of uncloneable encryption in which several possible decryption keys can decrypt a particular encryption.
We show that this variant of uncloneable encryption can be achieved device-independently.
We show that a simple modification of our scheme yields a single-decryptor encryption scheme.
arXiv Detail & Related papers (2022-10-03T16:17:01Z) - Uncloneable Decryptors from Quantum Copy-Protection [0.38073142980733]
We show that CPA secure uncloneable bit decryptors could be instantiated from a copy protection scheme.
We then show how to strengthen the CPA security of uncloneable decryptors to CCA2 security using strong EUF-CMA secure digital signatures.
arXiv Detail & Related papers (2022-03-11T11:47:04Z) - A brief history on Homomorphic learning: A privacy-focused approach to
machine learning [2.055949720959582]
Homomorphic encryption allows running arbitrary operations on encrypted data.
It enables us to run any sophisticated machine learning algorithm without access to the underlying raw data.
It took more than 30 years of collective effort to finally find the answer "yes"
arXiv Detail & Related papers (2020-09-09T21:57:47Z) - Towards Face Encryption by Generating Adversarial Identity Masks [53.82211571716117]
We propose a targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
TIP-IM provides 95%+ protection success rate against various state-of-the-art face recognition models.
arXiv Detail & Related papers (2020-03-15T12:45:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.