Shuren Qi

Dr. Shuren Qi


Research Focus & Metrics

Academic Career Length

5Years (2022-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.

5 January 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
CWChao Wang
Chao Wang
ZHZhiqiu Huang
Zhiqiu Huang
SQShuren Qi
Shuren Qi
YYYaoshen Yu
Yaoshen Yu
GSGuohua Shen
Guohua Shen
YZYushu Zhang
Yushu Zhang
Copy-move forgery is a manipulation of copying and pasting specific patches from and to an image, with potentially illegal or unethical uses. Recent advances in the forensic methods for copy-move forgery have shown increasing success in detection accuracy and robustness. However, for images with high self-similarity or strong signal corruption, the existing algorithms often exhibit inefficient processes and unreliable results. This is mainly due to the inherent semantic gap between low-level visual representation and high-level semantic concept. In this paper, we present a very first study of trying to mitigate the semantic gap problem in copy-move forgery detection, with spatial pooling of local moment invariants for midlevel image representation. Our detection method expands the traditional works on two aspects: 1) we introduce the bag-of-visual-words model into this field for the first time, may meaning a new perspective of forensic study; 2) we propose a word-to-phrase feature description and matching pipeline, covering the spatial structure and visual saliency information of digital images. Extensive experimental results show the superior performance of our framework over state-of-the-art algorithms in overcoming the related problems caused by the semantic gap.

16 January 2024 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
WWWenying Wen
Wenying Wen
HHHaigang Huang
Haigang Huang
SQShuren Qi
Shuren Qi
YZYushu Zhang
Yushu Zhang
YFYuming Fang
Yuming Fang
With the rapid development of internet applications, privacy protection of secret messages in covert communication has become increasingly important. To address the issue of attacks received in covert communication, such as eavesdropping attacks, steganalysis attacks, and tempering attacks, we propose a novel scheme that combines coverless steganography and image transformation for the covert communication of secret messages. Instead of using an image as the carrier to embed secret messages, our coverless steganography approach hides secret messages by exploiting a generative network to take it and a latent as input to synthesize a stego image, thus essentially avoiding both eavesdropping and typical steganalysis attacks. Furthermore, the generated pseudorealistic stego image with distortion vulnerabilities leads to tampering, which ultimately results in the receiver not being able to correctly extract secret information. In response to this problem, we design an image transformation method, which converts the stego image into another realistic image (i.e., camouflage image) and thus provides ambiguity for spoofing attackers while preventing stego images from being tampered with. Additionally, the authentication information is embedded into the camouflage image to obtain the transmitted authentication image ( $AuI$ ) and can be used by the receiver to validate the completeness and authenticity of the camouflage image. Compared with related steganography methods in recent years, our proposed scheme synthesizes more high-quality stego images, and the stego image can be restored losslessly from the camouflage image. Most importantly, the PSNR of the camouflage image with authentication information (i.e., $AuI$ ) is 31.78, which is enough to deceive the attacker; moreover, the secret message extraction rate can reach 100%.

11 December 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
TLTing Luo
Ting Luo
YZYuhang Zhou
Yuhang Zhou
ZHZhouyan He
Zhouyan He
GJGangyi Jiang
Gangyi Jiang
HXHaiyong Xu
Haiyong Xu
YZYushu Zhang
Yushu Zhang
Multi-image steganography ensures privacy protection while avoiding suspicion from third parties by embedding multiple secret images within a cover image. However, existing multi-image steganographic methods fail to model global spatial correlations to reduce image damage at the low computation cost. Moreover, they do not account for the anti-distortion capability of the cover image, which is crucial for achieving imperceptible and ensuring security. To overcome these limitations, we propose StegMamba, a distortion-free immune-cover for multi-image steganography architecture with a state space model. Specifically, we first explore the potential of the linear computational cost model Mamba for data hiding tasks through a steganography Mamba block (SMB), whose efficiency makes it suitable for real-time applications. Subsequently, considering that images with distortion resistance reduce embedding damage, the original cover image is reconstructed through immune-cover construction module (ICCM) and associated with the steganography task. Moreover, well-coupled features facilitate fusion, and thus a wavelet-based interaction module (WIM) is designed for effective communication between the immune-cover and the secret images. Compared with the state-of-the-art global attention-based methods, the proposed StegMamba obtains PSNR gains of 3.30 dB, 1.37 dB, and 1.92 dB for the stego image, and two secret recovery images, respectively, and the reduction of 2.87% in detection accuracy for anti-steganalysis. This code is available at https://github.com/YuhangZhouCJY/StegMamba.

8 September 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SQShuren Qi
Shuren Qi
YZYushu Zhang
Yushu Zhang
CWChao Wang
Chao Wang
JZJiantao Zhou
Jiantao Zhou
XCXiaochun Cao
Xiaochun Cao
Image forensics is a rising topic as the trustworthy multimedia content is critical for modern society. Like other vision-related applications, forensic analysis relies heavily on the proper image representation. Despite the importance, current theoretical understanding for such representation remains limited, with varying degrees of neglect for its key role. For this gap, we attempt to investigate the forensic-oriented image representation as a distinct problem, from the perspectives of theory, implementation, and application. Our work starts from the abstraction of basic principles that the representation for forensics should satisfy, especially revealing the criticality of robustness, interpretability, and coverage. At the theoretical level, we propose a new representation framework for forensics, called dense invariant representation (DIR), which is characterized by stable description with mathematical guarantees. At the implementation level, the discrete calculation problems of DIR are discussed, and the corresponding accurate and fast solutions are designed with generic nature and constant complexity. We demonstrate the above arguments on the dense-domain pattern detection and matching experiments, providing comparison results with state-of-the-art descriptors. Also, at the application level, the proposed DIR is initially explored in passive and active forensics, namely copy-move forgery detection and perceptual hashing, exhibiting the benefits in fulfilling the requirements of such forensic tasks.

6 February 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
YZYushu Zhang
Yushu Zhang
QTQing Tan
Qing Tan
SQShuren Qi
Shuren Qi
MXMingfu Xue
Mingfu Xue
Photo-response non-uniformity (PRNU), as a class of device fingerprint, plays a key role in the forgery detection/localization for visual media. The state-of-the-art PRNU-based forensics methods generally rely on the multi-scale trace analysis and result fusion, with Markov random field model. However, such hand-crafted strategies are difficult to provide satisfactory multi-scale decision, exhibiting a high false-positive rate. Motivated by this, we propose an end-to-end multi-scale decision fusion strategy, where a mapping from multi-scale forgery probabilities to binary decision is achieved by a supervised deep fully connected neural network. As the first time, the deep learning technology is employed in PRNU-based forensics for more flexible and reliable integration of multi-scale information. The benchmark experiments exhibit the state-of-the-art accuracy performance of our method in both pixel-level and image-level, especially for false positives. Additional robustness experiments also demonstrate the benefits of the proposed method in resisting noise and compression attacks.