How to Read Your Scan Results
Reality Defender returns a decision-ready signal with enough transparency to stand up in high-trust environments.
Most scans return three things:
Overall Results Score — a number produced by Reality Defender's models indicating the likelihood that the content has been manipulated or AI-generated
Final Conclusion — the actionable label (Authentic, Suspicious, or Manipulated) determined by Reality Defender's models. When enabled, Context and Metadata analysis may influence this conclusion.
Model indicators — visual signals showing which detection models were triggered
The overall score reflects the likelihood of manipulation — not the amount of manipulation present, and not whether every frame, second, or pixel is synthetic.
Note: When metadata analysis drives the final conclusion, no overall score appears. The conclusion is set directly by that analysis. Model indicators remain accessible in the Models tab.
Each detection model specializes in a different type of manipulation or synthesis method. Some models look at artifacts, others at context, content patterns, temporal dynamics, or linguistic signals. The final conclusion reflects a weighted consensus across all models that were triggered.
Conclusions
Reality Defender normalizes results into three conclusions across audio, image, and video. Each conclusion corresponds to a score range on a 0–100 scale.
Authentic (0-44) — low likelihood of manipulation or AI generation; continue normal workflows
Suspicious (45-55) — moderate likelihood of manipulation; worth a closer look or human review
Manipulated (56-100) — high likelihood that the content has been manipulated or AI-generated; trigger escalation or secondary validation
A higher overall score means a higher likelihood of manipulation — not that the entire file is synthetic.
When RealScan cannot return a standard result
In some cases, RealScan may not be able to return a standard Authentic or Manipulated result. This can happen when media is skipped during preprocessing, when the file does not contain enough usable signal for analysis, or when a processing issue prevents Reality Defender from completing the scan.
When this happens, the scan result may include a plain-language reason, such as limited usable audio, a model-specific evaluation issue, or a preprocessing error.
Note: Detailed error explanations appear only for new imports created after July 16, 2026. Older scans may still show a generic inconclusive or unable-to-evaluate result because they do not include the fields required to display detailed explanations.
🔈 Understanding Audio Results
When analyzing audio, Reality Defender evaluates indicators of voice synthesis, voice cloning, or audio splicing. The Models tab displays the overall score alongside model indicators showing which models were triggered.
Models used
Advanced — detects AI-generated audio using a larger foundation model trained on highly diverse synthesized-speech datasets. Looks for neural vocoder artifacts, frequency-domain anomalies, and model-specific generation fingerprints.
Generalizable — detects AI-synthesized audio using style and linguistic patterns unique to real human speech. Looks for unnatural prosody, overly consistent tone or pacing, and style mismatches common to audio LLMs.
How the final conclusion is determined
Both models produce independent signals, which are combined into a single overall score. Model indicators show which models were triggered.
📸 Understanding Image Results
Image detection evaluates synthetic or manipulated visual signals across AI-generated and traditionally edited images. Context and metadata analysis are available as additional layers and can be enabled or disabled by admins via settings.
Results are organized into three tabs: Models, Context, and Metadata.
Models
The Models tab displays the overall score alongside model indicators showing which models were triggered. These models analyze both facial regions and the full image frame.
Full Image
Full Image models analyze the entire image rather than only detected facial regions. They can surface manipulation signals across the body, background, or surrounding context.
Diffusion — detects images created by diffusion models (e.g. Midjourney, SDXL). Looks for diffusion sampling artifacts, uniform noise fields, and overly smooth textures.
Faceswaps — detects traditional and modern face swap-based manipulations. Looks for boundary inconsistencies, compositing artifacts, and identity mismatches.
GANs — detects images or faces generated or manipulated using generative adversarial network (GAN) methods. Looks for StyleGAN fingerprints, resolution-frequency mismatches, and geometric distortions.
Visual Noise Analysis — detects fake images by analyzing texture and distribution of visual noise. Looks for diffusion-grid artifacts, upscaling inconsistencies, and frequency patterns common in GAN-generated images.
Faces
The Faces section applies the same detection techniques to detected facial regions when usable faces are present.
Note: models are optimized for images containing people.
Context
Context model analysis uses a vision-language model to evaluate an image for signs of AI generation, informed by contextual signals such as Reverse Image Search results, visible AI-generation watermarks, filename indicators, source context, and concrete visual artifacts. It relies on stronger evidence, so it may miss subtle or clean AI-generated images and is not meant to detect every kind of image manipulation.
The Context tab appears whenever Context analysis is enabled for a scan. Results are shown as two distinct signals: General Context, which provides a plain-language explanation when contextual signals suggest the image may have been manipulated. In addition, Reverse Image Search may also appear under a separate header with a clickable link to scrollable details.
When Context analysis is enabled but no signals are found, the tab displays: “No context signals to suggest this media has been manipulated.”
Note: Because Context Aware requires additional processing, enabling it may increase scan latency compared with scans where Context Aware is disabled. Admins can enable or disable Context Aware in Settings → RealScan → Enable context models.
When context models are enabled, Reality Defender may also send relevant media data to optional third-party sub-processors for contextual signal analysis. See our current list of sub-processors for details.
Metadata
Metadata analysis examines provenance signals embedded in the image file for indicators of AI generation or manipulation. This includes software tags embedded by common generation tools such as Stable Diffusion, Midjourney, DALL-E, and GPT Image, as well as C2PA provenance records indicating AI generation.
When markers are found, they appear as AI markers in this tab and the final conclusion is set to Manipulated. When no markers are found, an explicit empty state is shown — this means no provenance signals were detected, not that the image is confirmed authentic.
Metadata analysis is available for images only and can be enabled or disabled by admins via settings.
When metadata drives the final conclusion, no overall score appears.
How the final conclusion is determined
Each model contributes a signal, weighted by relevance. Face-focused and full-frame models are combined into a single overall score.
When metadata analysis detects AI generation markers, it overrides the model ensemble and sets the final conclusion to Manipulated. When no markers are found, models run as usual and the overall score reflects the ensemble output.
Context analysis runs alongside the models — if Context returns Manipulated but the models return Authentic, the final conclusion is set to Manipulated with no overall score. Model indicators remain accessible in the Models tab.
🎥 Understanding Video Results
Video detection evaluates frame-level, temporal, and contextual indicators of deepfake generation or manipulation. Results are organized into two tabs: Models and Context.
Models
The Models tab displays an overall score alongside model indicators showing which detection models were triggered. These models analyze both the full video frame and detected face regions. Full-frame models expand coverage beyond detected faces, while face-region models provide additional signal when usable faces are present.
Full frame
Dynamics — analyzes motion and temporal patterns across the full video frame, helping evaluate videos where faces are absent, small, blurry, heavily compressed, or not consistently detectable.
Universal — analyzes the full video frame for manipulation signals that may appear outside a detected face, including signals in the body, background, scene, or surrounding context.
Faces
Dynamics — analyzes detected face regions over time. Looks for frame-to-frame inconsistencies, motion artifacts, and lip-sync irregularities.
Guided — focuses on specific facial features known to differ between real and generated faces. Looks for eye-region anomalies, subtle facial-expression inconsistencies, and local generation fingerprints.
Universal — detects deepfake faces generated across many methods, including GANs, diffusion, and hybrid approaches. Looks for global artifact patterns and multi-method synthesis signals across detected face regions.
Note: Full-frame video expands coverage for a wider range of content, but it does not mean every video can be evaluated with the same confidence as clear face-to-camera footage.
Context
Context model analysis uses a vision-language model to evaluate video frames for signs of AI generation or manipulation, informed by contextual signals and concrete visual artifacts. It can provide additional signal when relevant evidence appears outside a detected face region, or when the video contains scenes where faces are absent, small, or unclear.
The Context tab appears whenever Context analysis is enabled for a video scan. Video Context results appear as General Context. Reverse Image Search does not apply to video.
When Context analysis is enabled but no signals are found, the tab displays: “No context signals to suggest this media has been manipulated.”
Note: Because Context Aware requires additional processing, enabling it may increase scan latency compared with scans where Context Aware is disabled. Admins can enable or disable Context Aware in Settings → RealScan → Enable context models.
When context models are enabled, Reality Defender may also send relevant media data to optional third-party sub-processors for contextual signal analysis. See our current list of sub-processors for details.
How the final conclusion is determined
Face-region and full-frame video models are combined into a single overall score. When a clear face is available, Reality Defender can use both face-region and full-frame signals. When no usable face is present, the full-frame path can still return a result.
Context analysis runs alongside the video models when enabled. Context can influence the conclusion when it finds strong signs of manipulation, especially when relevant evidence appears outside detected face regions. Model indicators remain accessible in the Models tab.
The overall score reflects the likelihood of manipulation — not the amount of manipulation present, and not whether every frame or person in the video is synthetic.
🔡 Understanding Text Results
Text detection evaluates whether text has been generated or heavily edited by a large language model (LLM).
Models used
Text Detector – Generative
Detects linguistic patterns characteristic of LLM-generated text.
Looks for:
Over-optimized phrasing
Statistical smoothness
Predictable structural patterns
Low-variance word choice
How the final conclusion is determined
Since text uses a single model type, the overall score reflects the model's likelihood assessment directly.
If Your Result Seems Unexpected
Content may test as manipulated due to:
Heavy compression or filtering
AI-assisted editing
Image upscaling or enhancement
Non-human voices (e.g., IVR, TTS, synthetic accents)
AI-generated copy mixed with human text
Blend of real and generated segments
If you have questions about a specific file, use the "Report an Issue" button at the top right corner of your Scan Results page, or contact support@realitydefender.com.
Downloading Reports
Every completed scan can be exported as a PDF or CSV report containing: upload timestamp, detected modality and file metadata, triggered model indicators, overall score, and final conclusion with explanation.
Reports are timestamped and can be shared internally for record-keeping or audits.