Ment of image editing tactics, manipulating photos is becoming an easy task by means of different computer software, for example Photoshop, Meitu, etc., and brings a brand new challenge for the digital image forensics neighborhood. As a way to confirm the authenticity and integrity of a digital image, various algorithms [1] have been proposed. One of many most significant research subjects within the field of digital image forensics is contrast enhancement forensics. Being a basic however efficient image processing operation, Contrast enhancement (CE) is commonly used by malicious image attackers to remove inconsistent brightness when creating visually imperceptible tampered pictures. CE detection algorithms play a vital role in selection analysis from the authenticity and integrity of digital photos. Although some schemes happen to be proposed to detect contrast-enhanced pictures, the overall performance of such tactics is restricted in the circumstances of pre-JPEG compression and antiforensic attacks. As a result, it truly is critical to create robust and successful CE forensics algorithms. Due to the efforts of researches in the past decade, quite a few schemes [53] happen to be proposed to discriminate contrast-enhanced photos in an uncompressed format. Stamm et al. [5] identified that contrast enhancement introduced peaks and gaps into the image’s gray-level histogram, which led to particular high values in high-frequency components. Lin et al. [10,11] revealed that contrast enhancement would disturb the interchannel correlation left by color image interpolation and measured such correlation to distinguish the enhanced photos from the original images. In addition, in order toPublisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Copyright: 2021 by the authors. Licensee MDPI, Basel, Switzerland. This short article is definitely an open access post distributed below the terms and circumstances from the Inventive Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/).Entropy 2021, 23, 1318. https://doi.org/10.3390/ehttps://www.mdpi.com/journal/entropyEntropy 2021, 23,two ofrecover the image processing history, a lot of algorithms for estimating parameters for contrast-enhanced images have been created [147]. Despite the great efficiency obtained by the abovementioned algorithms, their robustness could be unsatisfactory in some cases, including the CE of JPEG photos (preJPEG compression) plus the occurrence of antiforensic attacks [183]. The purpose lies within the truth that the fingerprint left by CE operation could be altered. Primarily based on such a phenomenon, some researchers have proposed a lot more robust CE forensic algorithms, which is often divided into two significant branches: overcoming pre-JPEG compression [8] and defending against antiforensic attacks [13]. Regrettably, neither one of these strategies is capable of addressing both pre-JPEG compression and antiforensic attacks. To date, you can find no satisfactory solutions for these Tavilermide Protocol challenges. Using the fast improvement of deep-learning approaches, and in particular convolutional neural networks (CNNs), some researchers have recently attempted to utilize them for digital image forensics. Quite a few preliminary operates exploring CNNs within a single domain (like the pixel domain [24], the histogram domain [25], and also the gray-level co-occurrence matrix (GLCM) [26,27]) have Z-FA-FMK Technical Information already been proposed for CE forensics. As outlined by the report [26], deep-learning-based CE forensic schemes achieved greater functionality than traditio.