Hiding Private Information in Images From AI

Xue, Hanyu; Liu, Bo; Ding, Ming; Song, Li; Zhu, Tianqing

doi:10.1109/icc40277.2020.9148656

Cited by 13 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we suggest the addition of self-checking the possibility of COVID-19 infection service using a pre-trained AI model in the Apple-Google contact tracing platform. This service is based on AI algorithms and non-private data, and these kinds of services have already shown great promise in recent times [28]. The IPO (input, processing, and output) of the services is given below.…”

Section: Self-checking the Possibility Of Covid-19 Infection Using Ai...mentioning

confidence: 99%

Technical Analysis of Contact Tracing Platform Developed by Google–Apple for Constraining the Spread of COVID-19

Majeed

2022

IJGI

View full text Add to dashboard Cite

Amid the ongoing COVID-19 pandemic, technical solutions (e.g., smartphone apps, web-based platforms, digital surveillance platforms, etc.) have played a vital role in constraining the spread of COVID-19. The major aspects in which technical solutions have helped the general public (or health officials) are contact tracing, spread prediction, trend forecasting, infection risk estimation, hotspot identification, alerting people to stay away from contaminated places, hospitalization length estimation, clinical severity analysis, and quarantine monitoring, to name a few. Apart from other services, contact tracing has been extensively performed with the help of Bluetooth and GPS-powered smartphone applications when vaccines were unavailable. In this article, we technically analyze the contact tracing platform developed by Google–Apple for constraining the spread of COVID-19. We suggest unexplored technical functionalities that can further strengthen the platform from privacy preservation, service scenarios, and robustness point of view. Lastly, some AI-based and privacy-assured services that can be integrated with the platform to control the pandemic adequately are suggested. The technical analysis demonstrates that while the Google–Apple platform is well-engineered, it is not free of vulnerabilities, weaknesses, and misconfigurations that may lead to its poor adoption in real-life scenarios. This work can serve as a guideline for further enhancing the practicality of contact tracing platform to effectively handle future infectious diseases.

show abstract

Section: Self-checking the Possibility Of Covid-19 Infection Using Ai...mentioning

confidence: 99%

Technical Analysis of Contact Tracing Platform Developed by Google–Apple for Constraining the Spread of COVID-19

Majeed

2022

IJGI

View full text Add to dashboard Cite

show abstract

“…Various defense techniques and mechanisms have been proposed to enhance privacy by de-identifying face images. 1 Traditional obfuscation-based methods usually obfuscate the sensitive information by blurring, pixelating, or masking an image, which are illustrated in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Face image de‐identification by feature space adversarial perturbation

Xue

Liu

Yuan

et al. 2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Privacy leakage in images attracts increasing concerns these days, as photos uploaded to large social platforms are usually not processed by proper privacy protection mechanisms. Moreover, with advanced artificial intelligence (AI) tools such as deep neural network (DNN), an adversary can detect people's identities and collect other sensitive personal information from images at an unprecedented scale. In this paper, we introduce a novel face image de‐identification framework using adversarial perturbations in the feature space. Manipulating the feature space vector ensures the good transferability of our framework. Moreover, the proposed feature space adversarial perturbation generation algorithm can successfully protect the identity‐related information while ensuring the other attributes remain similar. Finally, we conduct extensive experiments on two face image datasets to evaluate the performance of the proposed method. Our results show that the proposed method can generate real‐looking privacy‐preserving images efficiently. Although our framework has only been tested on two real‐life face image datasets, it can be easily extended to other types of images.

show abstract

“…To achieve this, privacy protection methods need to detect, and then cover/remove/replace sensitive content in images. Several recent studies have explored this direction [ 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ]. For example, Viola et al [ 8 ] used a sliding window detector to identify and blur the license plates in Google Street View images.…”

Section: Introductionmentioning

confidence: 99%

GAN-Based Differential Private Image Privacy Protection Framework for the Internet of Multimedia Things

Xue

Liu

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

With the development of the Internet of Multimedia Things (IoMT), an increasing amount of image data is collected by various multimedia devices, such as smartphones, cameras, and drones. This massive number of images are widely used in each field of IoMT, which presents substantial challenges for privacy preservation. In this paper, we propose a new image privacy protection framework in an effort to protect the sensitive personal information contained in images collected by IoMT devices. We aim to use deep neural network techniques to identify the privacy-sensitive content in images, and then protect it with the synthetic content generated by generative adversarial networks (GANs) with differential privacy (DP). Our experiment results show that the proposed framework can effectively protect users’ privacy while maintaining image utility.

show abstract

Hiding Private Information in Images From AI

Cited by 13 publications

References 15 publications

Technical Analysis of Contact Tracing Platform Developed by Google–Apple for Constraining the Spread of COVID-19

Technical Analysis of Contact Tracing Platform Developed by Google–Apple for Constraining the Spread of COVID-19

Face image de‐identification by feature space adversarial perturbation

GAN-Based Differential Private Image Privacy Protection Framework for the Internet of Multimedia Things

Contact Info

Product

Resources

About