How Accurate Is AI Photo Detection? What the Score Actually Tells You

What powers the analysis

CatfishTracker uses a large multimodal AI model to visually analyse uploaded photos. The model examines the image across eight analysis dimensions: signs of AI generation, deepfake artefacts, beauty app usage, facial reshaping, skin smoothing, background manipulation, stock or model photo indicators, and lighting inconsistencies. It returns a score from 0 to 100 and a verdict: authentic, suspicious, manipulated, or AI generated.

What the score means

The 0 to 100 score reflects how many signs of manipulation the model found and how strong those signals are. A score close to 100 means nothing suspicious was detected across all eight dimensions. A score close to 0 means strong signals of manipulation were present. Scores in the middle, roughly 40 to 70, indicate something looked off but wasn't conclusive. These are worth a second look, not an automatic verdict.

The score is not a probability that the person is a catfish. It's a measure of photo authenticity: whether the image itself shows signs of AI generation, heavy editing, or manipulation. A real person can have a low-scoring photo because of heavy filters. A catfish can have a high-scoring photo because they used a real, unedited stolen image. The score is one input, not the final word.

What it's genuinely good at

• ▸Detecting obvious AI-generated faces: faces from tools like Midjourney, DALL-E, and Stable Diffusion have characteristic artefacts (skin texture, ear shape, background coherence) that the model identifies reliably.
• ▸Flagging heavy Facetune and beauty app usage: excessive skin smoothing, digitally enlarged eyes, and reshaping leave visible traces the model catches well.
• ▸Identifying studio or stock photos used as profile pictures: professional lighting, unnatural perfection, and watermark artefacts are strong signals.
• ▸Spotting inconsistent lighting between a face and background, a common tell in composite or AI-generated images.
• ▸Conversation scam pattern detection: the conversation analyser is trained on documented scammer scripts and detects love bombing, off-platform requests, money asks, and urgency tactics with high consistency.

Known edge cases to be aware of

• ▸Filters and Snapchat lenses: light filters don't reliably lower the score. If someone always uses heavy filters, ask for an unfiltered photo.
• ▸Older photos: a photo that is five years old might be genuine but no longer look like the person. The tool analyses the photo, not whether it's current.
• ▸Screenshots of photos: adding a screenshot border, watermark, or platform UI around a photo can affect the analysis.
• ▸Very dark or backlit photos: insufficient lighting reduces the quality of analysis significantly.

Used alongside your own instincts and a willingness to ask for a live video call, CatfishTracker gives you a meaningful edge, but the best protection is always a combination of tools, not any single one.