Content-Aware Differential Privacy with Conditional Invertible Neural Networks

Tölle, Malte; Köthe, Ullrich; André, Fabrice; Meder, Benjamin; Engelhardt, Sandy

doi:10.1007/978-3-031-18523-6_9

Cited by 2 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the two domains consider different performance indicators and evaluation metrics. Anonymization aims at providing privacy-preserving guarantees, including face anonymization rate and non-reidentifiability (Gross et al 2005;Liu et al 2021;Croft, Sack, and Shi 2021;Tölle et al 2022), which implies additional mechanisms compared to the face-swapping methods that prioritize preserving facial attributes while reckoning the visual quality of the injected identity (Nirkin, Keller, and Hassner 2019;Xu et al 2022). Face Anonymization.…”

Section: Related Workmentioning

confidence: 99%

“…Identity Obfuscation Guarantees. To provide formal de-identification guarantees, we ground our work in the extensive theory on ϵ-differential privacy (ϵ-DP) and ϵlocal-differential privacy (ϵ-LDP, relevant when obfuscation should be performed without global knowledge) applied to identity-swapping functions (Duchi, Jordan, and Wainwright 2013;Dwork, Roth et al 2014;Abadi et al 2016;Yu et al 2020;Liu et al 2021;Croft, Sack, and Shi 2021;Tölle et al 2022;Qiu et al 2022). Let ψ : Z → Z be a function that performs ID obfuscation, i.e., taking an identity vector z and returning a new one z that maximizes d Z (z, z).…”

Section: Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation

Disguise without Disruption: Utility-Preserving Face De-identification

Cai,

Gao,

Planche

et al. 2024

AAAI

View full text Add to dashboard Cite

With the rise of cameras and smart sensors, humanity generates an exponential amount of data. This valuable information, including underrepresented cases like AI in medical settings, can fuel new deep-learning tools. However, data scientists must prioritize ensuring privacy for individuals in these untapped datasets, especially for images or videos with faces, which are prime targets for identification methods. Proposed solutions to de-identify such images often compromise non-identifying facial attributes relevant to downstream tasks. In this paper, we introduce Disguise, a novel algorithm that seamlessly de-identifies facial images while ensuring the usability of the modified data. Unlike previous approaches, our solution is firmly grounded in the domains of differential privacy and ensemble-learning research. Our method involves extracting and substituting depicted identities with synthetic ones, generated using variational mechanisms to maximize obfuscation and non-invertibility. Additionally, we leverage supervision from a mixture-of-experts to disentangle and preserve other utility attributes. We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Problem Formulationmentioning

confidence: 99%

Disguise without Disruption: Utility-Preserving Face De-identification

Cai,

Gao,

Planche

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Moreover, the two domains consider different performance indicators and evaluation metrics. Anonymization aims at providing privacy preserving guarantees, including face anonymization rate and non re-identifiability [26,46,15,66], which implies additional mechanisms compared to the face-swapping methods that prioritize preserving facial attributes while reckoning the visual quality of the injected identity [55,77]. Face Anonymization.…”

Section: Related Workmentioning

confidence: 99%

“…Identity Obfuscation Guarantees. To provide formal de-identification guarantees, we ground our work in the extensive theory on -differential privacy ( -DP) andlocal-differential privacy ( -LDP, relevant when obfuscation should be performed without global knowledge) applied to identity-swapping functions [21,22,5,79,46,15,66,59]. Let ψ : Z → Z be a function that performs ID obfuscation, i.e., taking an identity vector z and returning a new one z that maximizes d Z (z, z).…”

Section: Formalismmentioning

confidence: 99%

Disguise without Disruption: Utility-Preserving Face De-Identification

Cai¹,

Gao²,

Planche³

et al. 2023

Preprint

View full text Add to dashboard Cite

With the increasing ubiquity of cameras and smart sensors, humanity is generating data at an exponential rate. Access to this trove of information, often covering yetunderrepresented use-cases (e.g., AI in medical settings) could fuel a new generation of deep-learning tools. However, eager data scientists should first provide satisfying guarantees w.r.t. the privacy of individuals present in these untapped datasets. This is especially important for images or videos depicting faces, as their biometric information is the target of most identification methods. While a variety of solutions have been proposed to de-identify such images, they often corrupt other non-identifying facial attributes that would be relevant for downstream tasks.In this paper, we propose Disguise, a novel algorithm to seamlessly de-identify facial images while ensuring the usability of the altered data. Unlike prior arts, we ground our solution in both differential privacy and ensemble-learning research domains. Our method extracts and swaps depicted identities with fake ones, synthesized via variational mechanisms to maximize obfuscation and non-invertibility; while leveraging the supervision from a mixture-of-experts to disentangle and preserve other utility attributes. We extensively evaluate our method on multiple datasets, demonstrating higher de-identification rate and superior consistency than prior art w.r.t. various downstream tasks.

show abstract

Content-Aware Differential Privacy with Conditional Invertible Neural Networks

Cited by 2 publications

References 16 publications

Disguise without Disruption: Utility-Preserving Face De-identification

Disguise without Disruption: Utility-Preserving Face De-identification

Disguise without Disruption: Utility-Preserving Face De-Identification

Contact Info

Product

Resources

About