Image complexity and feature mining for steganalysis of least significant bit matching steganography
Information Sciences: an International Journal
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Novel stream mining for audio steganalysis
MM '09 Proceedings of the 17th ACM international conference on Multimedia
Neighboring joint density-based JPEG steganalysis
ACM Transactions on Intelligent Systems and Technology (TIST)
Derivative-based audio steganalysis
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Detection of Double-Compression in JPEG Images for Applications in Steganography
IEEE Transactions on Information Forensics and Security
IEEE Transactions on Circuits and Systems for Video Technology
Steganalysis of DCT-embedding based adaptive steganography and YASS
Proceedings of the thirteenth ACM multimedia workshop on Multimedia and security
MiFor '11 Proceedings of the 3rd international ACM workshop on Multimedia in forensics and intelligence
Shift recompression-based feature mining for detecting content-aware scaled forgery in JPEG images
Proceedings of the Twelfth International Workshop on Multimedia Data Mining
Identification of smartphone-image source and manipulation
IEA/AIE'12 Proceedings of the 25th international conference on Industrial Engineering and Other Applications of Applied Intelligent Systems: advanced research in applied artificial intelligence
Hi-index | 0.00 |
Digital multimedia forensics is an emerging field that has important applications in law enforcement, the protection of public safety, and notational security. As a popular image compression standard, the JPEG format is widely adopted; however, the tampering of JPEG images can be easily performed without leaving visible clues, and it is increasingly necessary to develop reliable methods to detect forgery in JPEG images. JPEG double compression is frequently used during image forgery, and it leaves a clue to the manipulation. To detect JPEG double compression, we propose in this paper to extract the neighboring joint density features and marginal density features on the DCT coefficients, and then to apply learning classifiers to the features for detection. Experimental results indicate that the proposed method delivers promising performance in uncovering JPEG-based double compression. In addition, we analyze the relationship among compression quality factor, image complexity, and the performance of our double compression detection algorithm, and demonstrate that a complete evaluation of the detection performance of different algorithms should necessarily include both the image complexity and double compression quality factor.