Pecam

Wu, Hao; Tian, Xuejin; Li, Minghao; Liu, Yunxin; Ananthanarayanan, Ganesh; Xu, Fengyuan

doi:10.1145/3447993.3448618

Cited by 36 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address the limitations associated with passive defense dependency, latency, and high overhead, several schemes [21]- [26] have shifted their focus towards active defense research. For instance, Seo et al [21] have presented an active moving target defense strategy for Unmanned Aerial Vehicles (UAVs) utilizing a Partially Observable Markov Decision Process (POMDP) threat model.…”

Section: Related Workmentioning

confidence: 99%

“…While enhancing the Quality of Service (QoS), this method prioritizes minimizing latency but does not explicitly address the protection of privacy information. Wu et al [26] proposed a method to enhance privacy in video streaming through secure reversible transformation based on GAN networks (PECAM). This approach removes some visual details without compromising user feature accuracy, thereby enhancing the security of user feature privacy.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

P²SPA: Privacy Preservation Strategy With Pseudo-Addresses for Edge Computing Networks

Du,

Zhang,

Yuan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In recent years, edge computing networks have been widely adopted to achieve low latency, save bandwidth, and improve flexibility. However, most of the current Edge Nodes (ENs) are in semi-trusted or untrusted environments, where interactions among users are unsafe. Therefore, providing cost-effective protection strategies for ENs under resource limitations remains a great challenge. To cope with this, we propose an edge computing model with "End-Edge-Cloud" collaborative services, and a Privacy Preservation Strategy with Pseudo-Addresses (P 2 SPA) is constructed to maximize the cost-effectiveness while protecting the location privacy of the ENs. We quantify the privacy protection preference of user information using the Analytic Hierarchy Process (AHP) to select the optimal EN. Considering the dynamic change in the attack frequency, a pseudo-address selection and updating strategy is constructed based on the Stackelberg game theory; thus, the optimal pseudo-address update frequency is achieved. Numerical estimations are performed to verify the effectiveness of the proposed P 2 SPA strategy. Compared with the existing methods, P 2 SPA achieves a compromise service strategy with satisfactory performance on both the defense effect and defense cost.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

P²SPA: Privacy Preservation Strategy With Pseudo-Addresses for Edge Computing Networks

Du,

Zhang,

Yuan

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Cao et al [19] proposes a personalized invertible DeID framework where protection and recovery are implemented by transforming disentangled ID vector with user-specified password. Wu et al [20] designs PECAM, which performs privacy-enhanced securely-reversible video transformation in video streaming and analytics systems. Li et al [21], [22] proposes identitypreserved facial anonymization via identity-aware region discovery to determine facial attributes sensitive to human eyes.…”

Section: B Deep-based Facial Anonymizationmentioning

confidence: 99%

“…When presenting the pre-obfuscated image to the recovery module, it is still hard to recover the correct image although the preobfuscated image is highly similar to the protection image. In practice, this feature allows us to apply the full protection procedure only on a few key video frames while keeping the other frames in pre-obfuscated form, similar as PECAM [20]. It will not only reduce computational burdens but also confuse potential attackers.…”

Section: Security Analysismentioning

confidence: 99%

PRO-Face: A Generic Framework for Privacy-preserving Recognizable Obfuscation of Face Images

Lin

Liu

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework. 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, thus ensuring privacy. The pre-obfuscation applied can be in diversified form with different strengths and styles specified by users. Along protection, a secret key is injected into the network such that the original image can only be recovered from the protection image via the same model given the correct key provided. Two modes of image recovery are devised to deal with malicious recovery attempts in different scenarios. Finally, extensive experiments conducted on three public image datasets demonstrate the superiority of the proposed framework over multiple state-of-the-art approaches.

show abstract

“…Compared with purely edge-based solution, one concern about cloudedge collaboration is the potential privacy violation, since it requires training data to be uploaded to cloud. However, some existing solutions [174,21,100] have proposed privacy-preserving video streaming and analytics techniques which adapt well to our cloud-edge collaborative architecture. Therefore, privacy issues are not considered but the system is compatible with such privacy-preserving designs.…”

Section: Benefit Of Collaborative Continuous Learningmentioning

confidence: 99%

Cross-layer host-network co-design for QoS in streamed video data networking

Nan

View full text Add to dashboard Cite

show abstract

Pecam

Cited by 36 publications

References 28 publications

P²SPA: Privacy Preservation Strategy With Pseudo-Addresses for Edge Computing Networks

P²SPA: Privacy Preservation Strategy With Pseudo-Addresses for Edge Computing Networks

PRO-Face: A Generic Framework for Privacy-preserving Recognizable Obfuscation of Face Images

Cross-layer host-network co-design for QoS in streamed video data networking

Contact Info

Product

Resources

About