DeepFakeCheck
Evidence-first AI checks for video, audio, image & text
Start new thread

DeepFakeCheck - Evidence-first AI checks for video, audio, image & text

by•
Review suspicious video, audio, images, and text in one place. DeepFakeCheck combines locally verified C2PA provenance when available, metadata clues, and AI-based analysis, then returns a clear risk rating with uncertainty notes instead of claiming proof. Video checks sample up to 10 frames across the full timeline. Free checks, no signup; uploads are not retained after the request completes.

Add a comment

Replies

Best
Maker
📌
Hi Product Hunt 👋 I built DeepFakeCheck after seeing how easily suspicious clips and voice notes get treated as either ‘obviously fake’ or ‘definitely real.’ Most tools return a single confidence score. I wanted a more honest workflow: check provenance when present, inspect metadata, run AI analysis, and show uncertainty instead of calling the result proof. You can try video, audio, image, or text without creating an account. I’d especially value feedback on whether the evidence is understandable and what would make it more useful for journalists, fraud triage, and everyday verification. Important: AI detectors can be wrong, so high-stakes decisions still need independent verification.

the no signup and no retention thing is honestly what got me to try it. ran a video through and liked that it showed uncertainty notes instead of a flat "real/fake" answer, kind of refreshing honestly.

Maker

 Really glad that stood out — privacy and honest uncertainty are two things we care deeply about. Thanks for actually testing it with a video. Was there any part of the evidence that felt unclear or missing?

Maker

Behind the launch: DeepFakeCheck is built for situations where a single confidence score isn’t enough—suspicious clips, voice notes, images, or text that need inspectable evidence. We combine C2PA provenance when present, metadata clues, and multimodal analysis, then keep uncertain cases uncertain. Our current image regression set includes 5 AI-generated and 7 real images. All 12 pass our release guardrails; in the first 10-image run, all 5 AI images stayed high risk, while none of the 5 real images were falsely marked high risk (3 difficult real images remained uncertain). Video regression currently covers 4 manipulated and 6 real clips. These are small regression guardrails, not a claim of universal accuracy.

One thing I'd love to see is a side-by-side comparison view that overlays the frame timing analysis with the audio waveform sync, so I can spot lip-sync drift at a glance. Would make the verification feel more transparent and help me trust the risk rating.

Maker

 Thanks, Berkay — you’re right that this would make the evidence much easier to inspect. One important caveat is that lip-sync drift isn’t proof of AI on its own: dubbing, editing, variable frame rates, capture latency, and platform transcoding can also cause it. We’re going to test a synchronized audio-visual check that compares mouth motion with speech activity and highlights timestamped drift windows, while treating it as supporting evidence rather than automatically raising the verdict. The frame + waveform view would make both the signal and that uncertainty visible. Appreciate the thoughtful suggestion.

A reverse image and audio search would be a great add, even if it pulls from a small curated set of fact checking sources. It would help catch clips that are old or out of context, which feels like the most common type of misinformation I see in family group chats.

Maker

 Thank you, Halime — we took this seriously. Your suggestion pushed us to prioritize it immediately, and we shipped a first version during launch day. DeepFakeCheck now adds Public source traces to image checks, looking for full and partial public matches and the pages where an image appeared.

In this test, the model stayed UNCERTAIN at 74%, while source search found 10 full public matches — exactly the kind of extra context you described. I’ve attached the result. Matches are supporting clues, not proof, and reverse audio search is still on our roadmap.

Maker

Launch-day update: Public source traces are live.

We tested it with an English Wikimedia Commons image explicitly labeled “AI-generated deepfake hoax image of the Hollywood sign during the 2025 California wildfires.” DeepFakeCheck returned an UNCERTAIN 74% AI risk score, while the source layer found 10 full public matches.

That contrast is why we’re evidence-first: the model alone was not conclusive, but public source traces added useful context. Matches are supporting clues, not proof.

Source:

Try it:

One thing that would make this even more useful is a side by side comparison view showing the specific frames or audio segments that triggered the risk flag, so users can see exactly what the analysis picked up rather than just reading a score.

Maker

 Thanks, Ceylin — this is already available for image and video checks. On desktop, the evidence snapshot sits beside the risk rating, and video findings are linked to timestamped frames so you can inspect what contributed to the assessment. Segment-level audio visualization isn’t available yet, and all signals remain supporting evidence rather than proof.