Histogram based forensic techniques to detect contrast enhancement, after an initial success, became unreliable due to the development of targeted anti-forensic attacks. These attacks eliminate statistical footprints left by enhancement on the histogram, making the image modifications undetectable. Further, these techniques in-spite of being successful in making histograms of the enhanced image appear more natural, they themselves introduce anomalies in the spatial domain. This paper presents a novel algorithm that, for the first time, exploits the statistical anomalies through the Laplace modeling of the derivative histogram to detect the anti-forensic contrast enhancement. Experimental results demonstrate that the proposed algorithm is effective in detecting contrast enhancements executed both by regular as well as anti-forensics techniques. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.