Sample Image Authenticity Reports

Adobe Firefly AI-generated image sample report

FauxScan classified this walking-dog image as AI-generated because embedded Content Credentials identify Adobe Firefly as the signed generator. The provenance record carries more weight than an uncorroborated human-origin detector result.

What FauxScan found: The scan found valid C2PA credentials, Adobe Firefly generator metadata, an Adobe signer, a trained-algorithmic-media source type, no EXIF metadata, and forensic signals consistent with generated or heavily processed imagery.
C2PA and provenance: C2PA was present, embedded, and valid. The manifest names Adobe Firefly as generator and producer, identifies Adobe Inc. as issuer, and includes an AI model reference for gemini-flash.
Metadata: No camera EXIF metadata was present, which means the file did not carry normal camera make, model, capture, or GPS context. The PNG was analyzed with native pixel-domain residual checks instead of JPEG ELA.
Why it matters: This sample shows how verified provenance can resolve conflicts when an AI detector alone points the wrong way. A reviewer can explain the verdict by pointing to signed source data instead of relying on a single model score.
Limitations: The report does not prove where the image was first published or whether it was used deceptively. Residual analysis is a supporting signal, not standalone proof of manipulation.

Open interactive sample report

Google Gemini AI watermark sample report

FauxScan classified this beach-working image as AI-generated because the file contains valid Content Credentials signed by Google and a visible Google Gemini AI watermark.

What FauxScan found: The scan found embedded valid C2PA credentials, a Google signer, a composite-with-trained-algorithmic-media source type, no EXIF metadata, visible AI watermark evidence, residual texture signals, and frequency artifacts.
C2PA and provenance: C2PA was present, embedded, and valid. The manifest identifies Google C2PA Core Generator Library metadata and Google Media Processing Services as the signer.
Metadata: The image did not include camera EXIF metadata or GPS context. Because the source is PNG, FauxScan uses native pixel residual analysis instead of JPEG ELA.
Why it matters: This sample demonstrates a high-confidence provenance case: the watermark, C2PA record, and forensic signals all point toward AI generation even when a detector result alone is not reliable.
Limitations: The report verifies strong AI-origin indicators, but it does not identify the uploader, original prompt, publication path, or user intent behind the image.

Open interactive sample report

Adobe Firefly AI-modified image sample report

FauxScan classified this coffee image as AI-modified because verified Adobe Firefly Content Credentials identify algorithmic media involvement. The result should be treated as an edited or generated derivative, not an untouched camera original.

What FauxScan found: The scan found valid embedded C2PA credentials, Adobe Firefly generator and signer data, missing camera metadata, residual texture findings, frequency artifacts, and no clear sensor-pattern evidence.
C2PA and provenance: C2PA was present, embedded, and valid. The provenance record names Adobe Firefly, Adobe Inc., and a trained-algorithmic-media source type.
Metadata: No EXIF camera metadata was present. Without camera make, model, or capture context, the provenance record becomes the main source of origin evidence.
Why it matters: This sample helps reviewers distinguish AI-modified content from purely AI-generated content and from ordinary camera-origin photos that have simply been exported or recompressed.
Limitations: The report does not show the exact edited region or prove the edit's purpose. Residual and frequency signals support review, but the signed provenance record is the strongest evidence.

Open interactive sample report

Likely authentic iPhone photo sample report

FauxScan classified this Vessel NYC image as likely authentic because it contains Apple iPhone metadata, GPS coordinates, and no localized JPEG recompression mismatch.

What FauxScan found: The scan found iPhone 15 Pro metadata, iOS software metadata, GPS coordinates near Hudson Boulevard East in New York, a human-origin detector result, and no localized JPEG Ghost mismatch.
C2PA and provenance: No C2PA Content Credentials were found. The verdict relies on device metadata, location metadata, and forensic consistency rather than signed provenance.
Metadata: Camera make, camera model, software version, and GPS coordinates were present. These are useful source-context signals, though they still need chain-of-custody review in high-stakes settings.
Why it matters: This sample shows how FauxScan can support likely camera-origin review even when there is no C2PA manifest. It also shows why provenance and metadata should be read alongside forensic signals.
Limitations: Likely authentic does not mean legally proven original. Metadata can be copied, stripped, or altered, and location context should be confirmed against the source file and surrounding evidence.

Open interactive sample report

Likely inauthentic image sample report

FauxScan classified this SUV image as likely inauthentic because it lacks verified provenance and camera metadata while carrying signals that require review before relying on it as an unaltered photo.

What FauxScan found: The scan found no C2PA credentials, no EXIF metadata, no clear sensor-pattern traces, a standardized aspect ratio, low ELA variation, and no localized JPEG recompression mismatch.
C2PA and provenance: No C2PA Content Credentials were found. That absence does not prove manipulation, but it removes an important source of signed origin evidence.
Metadata: No camera make, model, GPS, or capture metadata was present. The missing metadata limits the ability to connect the image to a real capture device.
Why it matters: This sample reflects a common review case where the tool cannot prove the source but can identify weak provenance and explain why a human reviewer should ask for the original file or corroborating context.
Limitations: The report does not prove that the image is fake or identify a pasted region. It flags weak authenticity support and recommends manual review before reliance.

Open interactive sample report

Authenticity unverified image sample report

FauxScan classified this plane image as authenticity unverified because important source-verification signals are missing. The file may be ordinary exported content, but the scan cannot establish camera origin.

What FauxScan found: The scan found no C2PA credentials, no camera make or model, no GPS metadata, a human-origin detector result, camera-like dimensions, native pixel residual analysis, and frequency signals that require context.
C2PA and provenance: No C2PA Content Credentials were found. Without signed provenance, the report cannot tie the file to a verified creator, capture device, or generation tool.
Metadata: The image lacked camera and GPS metadata. Because the source is PNG, FauxScan uses native pixel residual analysis and does not claim JPEG compression-history evidence.
Why it matters: This sample shows the value of an explicit unverified result. Instead of overclaiming, the report explains which evidence is absent and what a reviewer should confirm next.
Limitations: The result does not prove AI generation or manipulation. It mainly says that the available file does not carry enough provenance, metadata, or sensor evidence to support a stronger authenticity claim.

Open interactive sample report

Integrity compromised image sample report

FauxScan classified this bridge image as integrity compromised because boundary-level compression analysis found a strong localized anomaly consistent with a possible pasted region, sky replacement, or compositing boundary.

What FauxScan found: The scan found no C2PA credentials, no EXIF metadata, moderate ELA levels, a strong boundary-local compression anomaly, no localized JPEG Ghost mismatch, and a human-origin detector result.
C2PA and provenance: No C2PA Content Credentials were found. The integrity concern comes from image-forensic signals rather than signed provenance.
Metadata: No EXIF metadata was present, so the report could not use camera make, model, capture time, or GPS data to support source verification.
Why it matters: This sample shows how FauxScan can separate AI-origin questions from integrity questions. A human-origin detector result can coexist with localized evidence that the image may have been altered.
Limitations: The report does not prove exactly what was changed. Boundary and ELA findings should guide manual inspection, comparison to originals, and source-context review.

Open interactive sample report