Tao Wang

Dr. Tao Wang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 December 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
Tao WangTao Wang
Tao Wang
YZYushu Zhang
Yushu Zhang
SQShuren Qi
Shuren Qi
RZRuoyu Zhao
Ruoyu Zhao
ZXZhihua Xia
Zhihua Xia
JWJian Weng
Jian Weng
The advent of artificial intelligence-generated content (AIGC) represents a pivotal moment in the evolution of information technology. With AIGC, it can be effortless to generate high-quality data that is challenging for the public to distinguish. Nevertheless, the proliferation of generative data across cyberspace brings security and privacy issues, including privacy leakages of individuals and media forgery for fraudulent purposes. Consequently, both academia and industry begin to emphasize the trustworthiness of generative data, successively providing a series of countermeasures for security and privacy. In this survey, we systematically review the security and privacy on generative data in AIGC, particularly for the first time analyzing them from the perspective of information security properties. Specifically, we reveal the successful experiences of state-of-the-art countermeasures in terms of the foundational properties of privacy, controllability, authenticity, and compliance, respectively. Finally, we show some representative benchmarks, present a statistical analysis, and summarize the potential exploration directions from each of these properties.

8 May 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YZYushu Zhang
Yushu Zhang
Tao WangTao Wang
Tao Wang
RZRuoyu Zhao
Ruoyu Zhao
WWWenying Wen
Wenying Wen
YZYouwen Zhu
Youwen Zhu
The tremendous progress in deep learning has enabled to extract soft-biometric attributes from faces, which raises privacy concerns over images collected for face recognition. Advances toward attribute privacy have been able to conceal multiple attributes while preserving identity information but suffer from limitations: they 1) only consider a few soft-biometric attributes and 2) fail to support reversibility for attribute privacy preservation. To break these limitations, we design a reversible privacy-preserving scheme for various face attributes, called reversible attribute privacy preservation (RAPP). RAPP benefits from two modules: 1) The attribute obfuscator introduces a stream cipher to determine that special attributes have to be concealed with the user-defined password, which also supports recovering original attributes. 2) The attribute adversarial network is proposed to generate perturbed images that conceal various attributes while retaining the utility of face verification. In addition, when a wrong password is provided, the returned image with wrong attribute classification results still keeps realistic, which confuses an attacker to know whether the recovery is correct. Extensive experiments demonstrate that RAPP enables to conceal various attributes and recover original images while facilitating face verification.

24 January 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
RZRuoyu Zhao
Ruoyu Zhao
YZYushu Zhang
Yushu Zhang
Tao WangTao Wang
Tao Wang
WWWenying Wen
Wenying Wen
YXYong Xiang
Yong Xiang
XCXiaochun Cao
Xiaochun Cao
Vision is the most important sense for people, and it is also one of the main ways of cognition. As a result, people tend to utilize visual content to capture and share their life experiences, which greatly facilitates the transfer of information. Meanwhile, it also increases the risk of privacy violations, e.g., an image or video can reveal different kinds of privacy-sensitive information. Scholars have persistently pursued the advancement of tailored privacy protection measures. Various surveys attempt to consolidate these efforts from specific viewpoints. Nevertheless, these surveys tend to focus on particular issues, scenarios, or technologies, hindering a comprehensive overview of existing solutions on a broader scale. In this survey, a framework that encompasses various concerns and solutions for visual privacy is proposed, which allows for a macro understanding of privacy concerns from a comprehensive level. It is based on the fact that privacy concerns have corresponding adversaries, and divides privacy protection into three categories, based on computer vision (CV) adversary, based on human vision (HV) adversary, and based on CV & HV adversary. For each category, we analyze the characteristics of the main approaches to privacy protection, and then systematically review representative solutions. Open challenges and future directions for visual privacy protection are also discussed.

26 June 2023 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
Tao WangTao Wang
Tao Wang
YZYushu Zhang
Yushu Zhang
RZRuoyu Zhao
Ruoyu Zhao
WWWenying Wen
Wenying Wen
RLRushi Lan
Rushi Lan
Massive face images collected in smart surveillance and social networks are vulnerable to malicious access, thus compromising individual privacy. Existing schemes have been able to protect face privacy while preserving a certain level of identifiability, but have different limitations, e.g., the lack of strong transferability or the inability to retain irrelevant attributes. This letter proposes a novel face privacy protection scheme via virtual identity transformation, which guarantees strong privacy protection and high identifiability. We first solve a specific identity mask for the user, which ensures that the identity features extracted only from the user's faces can be approximated to the given virtual identity. Based on it, the identity transformation networks transform the original face into the protected form, which belongs to the virtual identity while retaining irrelevant attributes. Lastly, the virtual identity of the protected face is extracted for face recognition. Adequate experiments show that our scheme has satisfactory privacy protection, high identifiability, and strong transferability.

13 February 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
Tao WangTao Wang
Tao Wang
WWWenying Wen
Wenying Wen
XXXiangli Xiao
Xiangli Xiao
Zhongyun HuaZhongyun Hua
Zhongyun Hua
YZYushu Zhang
Yushu Zhang
YFYuming Fang
Yuming Fang
The prevalence of face capturing along with the advancement of face recognition poses a potential threat to individual privacy. To protect privacy, plenty of methods have been proposed to change identity in the face, thus blocking malicious face recognition. However, these methods fail to satisfy authentication requirements for special application scenarios, e.g., face authentication in surveillance capture. In this paper, we propose a novel face privacy protection model, which supports robust image authentication via information-conditional identity transformation. Specifically, we first introduce a basic face manipulation model (FMM), which can preserve identity-irrelevant attributes when manipulating identity. Based on FMM, we further design a lightweight protector called AIDPro, outputting a transformed identity which is different from the original one and is embedded a message presenting authentication information. Benefiting from the semantic robustness, our model does not require noise layers to achieve accurate message extraction after various image distortions. In addition, the message can be the condition to guide the identity transformation for privacy protection, which avoids extra resource consumption from supporting image authentication. Extensive experimental results demonstrate our model has comparable privacy protection performance, superior attribute preservation performance, and robust authentication performance especially in JPEG compression and screen shooting. Our code is available at https://github.com/daizigege/AIDPro.

28 October 2024
Verified
Conference Paper
Open access
Tao WangTao Wang
Tao Wang
YZYushu Zhang
Yushu Zhang
XXXiangli Xiao
Xiangli Xiao
LYLin Yuan
Lin Yuan
ZXZhihua Xia
Zhihua Xia
JWJian Weng
Jian Weng
The significant advancement in face recognition drives face privacy protection into a prominent research direction. Unlike de-identification, a recent class of face privacy protection schemes preserves identifiable formation for face recognition. However, these schemes fail to support the revocation of the leaked identity, causing attackers to potentially identify individuals and then pose security threats. In this paper, we explore the possibility of generating privacy-preserving faces (not features) supporting cancelable biometric recognition. Specifically, we propose a cancelable face generator (CanFG), which removes the physical identity for privacy protection and embeds the virtual identity for face recognition. Particularly, when leaked, the virtual identity can be revoked and renew as another one, preventing re-identification from attackers. Benefiting from the designed distance-preserving identity transformation, CanFG can guarantee separability and preserve recognizability of virtual identities. Moreover, to make CanFG lightweight, we design a simple but effective training strategy, which allows CanFG to require only one (rather than two) network for achieving stable multi-objective learning. Extensive experimental results and sufficient security analyses demonstrate the ability of CanFG to effectively protect physical identity and support cancelable biometric recognition. Our code is available at https://github.com/daizigege/CanFG.