Step-by-Step: Checking Photo Authenticity and Detecting Manipulation

Not sure whether a photo, receipt, or ID has been doctored? You can't always tell by eye, but an image carries forensic traces of how it was made and edited. This guide walks through checking a picture with on-device analysis — nothing is uploaded, so even a confidential image stays on your machine.

Open the Image Authenticity Checker

Head to the Image Authenticity Checker and drop your image onto the page. It loads and analyses locally in your browser. Keep in mind that forensics is advisory: these tools surface signals, not verdicts.

Run Error Level Analysis (ELA)

ELA re-saves the image and compares compression levels across it. Regions that were pasted in or edited often compress differently from the rest, showing up as brighter or oddly uniform areas. Look for patches whose error level doesn't match their surroundings.

Audit the JPEG quality and quantization

The tool reads the raw JPEG quantization tables to estimate the true quality and detect signs of re-saving. A photo that claims to be an original but shows double-compression artefacts has been through an editor at least once.

Inspect the block grid and resampling

Cropping, resizing and splicing disturb the regular 8×8 JPEG block grid and leave resampling patterns. A broken or misaligned grid in one area is a classic sign that part of the image was altered or inserted.

Read the noise map

Cameras add a consistent sensor-noise fingerprint across a genuine photo. Where that noise floor suddenly changes, content may have been spliced in from another source.

Weigh the signals together

No single test proves manipulation. Treat the results as evidence to weigh: several independent signals pointing the same way is far stronger than one. Because the whole analysis runs on your device, you can examine sensitive documents without ever exposing them.

Pair this with a metadata check: mismatched timestamps or editing-software tags in the EXIF are another strong tell.