REPOGEO REPORT · LITE

MadryLab/photoguard

Default branch main · commit 686bea75 · scanned 6/2/2026, 11:53:21 AM

GitHub: 677 stars · 66 forks

AI VISIBILITY SCORE

40 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface MadryLab/photoguard, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Reposition the README's opening paragraph to clearly state user benefits

Why:

CURRENT

This repository contains the code for our recent work on safe-guarding images against manipulation by ML-powerd photo-editing models such as stable diffusion.

COPY-PASTE FIX

PhotoGuard is a tool designed to protect your images from unauthorized manipulation by AI-powered photo-editing models like Stable Diffusion. It applies imperceptible perturbations to your photos, making them resistant to deepfake generation and other malicious AI editing, ensuring your digital privacy and control.

hightopics#2

Add user-centric and application-oriented topics

Why:

CURRENT

adversarial-attacks, adversarial-examples, computer-vision, deep-learning, deepfakes, robustness, stable-diffusion

COPY-PASTE FIX

adversarial-attacks, adversarial-examples, computer-vision, deep-learning, deepfakes, robustness, stable-diffusion, image-protection, digital-privacy, ai-safety, content-authenticity

mediumreadme#3

Add a section clarifying PhotoGuard's unique approach and differentiation

Why:

COPY-PASTE FIX

## How PhotoGuard Works & Why It's Unique

Unlike traditional watermarking or general adversarial robustness toolkits, PhotoGuard applies imperceptible, targeted perturbations directly to your image pixels. These 'guards' are designed to specifically disrupt the internal mechanisms of generative AI models like Stable Diffusion, making your images unusable for malicious editing or deepfake generation without visible alteration to the original photo.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface MadryLab/photoguard

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Glaze

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Glaze · recommended 1×
Nightshade · recommended 1×
Photoshop · recommended 1×
StegCloak · recommended 1×
Visual Watermark · recommended 1×

CATEGORY QUERY
How to protect my images from AI-powered deepfake manipulation and editing?
you: not recommended
AI recommended (in order):
1. Glaze
2. Nightshade
3. Photoshop
4. StegCloak
5. Visual Watermark
6. Watermarkly
7. Digimarc
AI recommended 7 alternatives but never named MadryLab/photoguard. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Seeking tools to make AI image generation robust against adversarial editing attacks.
you: not recommended
AI recommended (in order):
1. CleverHans (tensorflow/cleverhans)
2. Foolbox (bethgelab/foolbox)
3. PyTorch-Adversarial (BorealisAI/pytorch-adversarial)
4. Stable Diffusion (Stability-AI/StableDiffusion)
5. ART - Adversarial Robustness Toolbox (IBM/adversarial-robustness-toolbox)
6. LPIPS - Learned Perceptual Image Patch Similarity (richzhang/PerceptualSimilarity)
7. OpenCV (opencv/opencv)
8. Pillow (python-pillow/Pillow)
AI recommended 8 alternatives but never named MadryLab/photoguard. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of MadryLab/photoguard?
pass
AI named MadryLab/photoguard explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts MadryLab/photoguard in production, what risks or prerequisites should they evaluate first?
pass
AI named MadryLab/photoguard explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo MadryLab/photoguard solve, and who is the primary audience?
pass
AI named MadryLab/photoguard explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of MadryLab/photoguard. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/MadryLab/photoguard.svg)](https://repogeo.com/en/r/MadryLab/photoguard)

HTML

<a href="https://repogeo.com/en/r/MadryLab/photoguard"><img src="https://repogeo.com/badge/MadryLab/photoguard.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

MadryLab/photoguard — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite