This paper presents a unified framework for identifying the source digital camera from its images and for detecting digitally altered images using photo-response non-uniformity (PRNU) noise, a unique stochastic fingerprint of imaging sensors. The PRNU is estimated using a Maximum Likelihood estimator derived from a simplified model of sensor output. The detection of PRNU in specific regions of an image is formulated as a hypothesis testing problem, with the statistical distribution of the test statistics obtained using a predictor of the test statistics on small image blocks. This enables more accurate estimation of false rejection rates and missed detection rates. The robustness of the proposed forensic methods is tested on common image processing tasks such as JPEG compression, gamma correction, resizing, and denoising. The paper includes a benchmark implementation and detailed experimental validation.This paper presents a unified framework for identifying the source digital camera from its images and for detecting digitally altered images using photo-response non-uniformity (PRNU) noise, a unique stochastic fingerprint of imaging sensors. The PRNU is estimated using a Maximum Likelihood estimator derived from a simplified model of sensor output. The detection of PRNU in specific regions of an image is formulated as a hypothesis testing problem, with the statistical distribution of the test statistics obtained using a predictor of the test statistics on small image blocks. This enables more accurate estimation of false rejection rates and missed detection rates. The robustness of the proposed forensic methods is tested on common image processing tasks such as JPEG compression, gamma correction, resizing, and denoising. The paper includes a benchmark implementation and detailed experimental validation.