Deploy Bravely with the world’s most comprehensive AI security platform securing your AI agents, apps, models and data at every step. ModelScan is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/modelscan. Directory filing: Model / data poisoning detection. Vendor legal name on this product record: Protect AI, Inc. ModelScan is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/modelscan. Directory filing: Model / data poisoning detection.
Category: Model / data poisoning detection
Product listing
ModelScan
From Protect AI
Share image from their website · not a live screen grab · not verified evidence
AI Software Product · Model / data poisoning detection · AI Safety & Security
- Unclaimed
- Directory-only
Ranking status: Directory only — not ranked
TrustMark reading
Where this product sits
ModelScan is classified as Model / data poisoning detection. Finding poisoned training data or backdoored models. Jobs: training-set scans; backdoor tests; supply-chain of weights.
Buyers typically come to Model / data poisoning detection because training sets and fine-tunes can carry backdoors nobody tests for. Classification is not a finding that this product solves that job.
This is TrustMark's classification reading for buyers comparing Model / data poisoning detection products. It is not an Assurance Score, certificate, or ranked position.
What it is
Product classification
AI Software Product
Deploy Bravely with the world’s most comprehensive AI security platform securing your AI agents, apps, models and data at every step. ModelScan is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/modelscan. Directory filing: Model / data poisoning detection. Vendor legal name on this product record: Protect AI, Inc. ModelScan is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/modelscan. Directory filing: Model / data poisoning detection.
Model / data poisoning detection · AI Safety & Security
What it does
How this product is used
- Capabilities
- Not specified
- Sectors
- Cross-industry / not specified
- Deployment
- Not specified
- Autonomy
- ASSISTIVE
- Data exposure
- Not specified
Verified claims
What has been independently checked
- Independently verified· 2026-09-17Domain association: Verified
- This only confirms the listing is tied to a checked company website domain. It is not a product assessment, certificate, review star, or ranked position.
Supplier-provided information
AI TrustMark has not independently verified supplier-provided marketing claims on this profile, including untested productivity, ROI or performance figures, unless they appear under verified claims or a named certificate. Absence of a claim from the verified list means it has not been evidenced here.
What the vendor’s website says · supplier-provided, not verified evidence
Deploy Bravely with the world’s most comprehensive AI security platform securing your AI agents, apps, models and data at every step. ModelScan is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/modelscan. Directory filing: Model / data poisoning detection. Vendor legal name on this product record: Protect AI, Inc. ModelScan is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/modelscan. Directory filing: Model / data poisoning detection.
Claim this listing to add a supplier statement alongside the website summary.
Category context
Why buyers look at Model / data poisoning detection
Finding poisoned training data or backdoored models. Jobs: training-set scans; backdoor tests; supply-chain of weights.
Training sets and fine-tunes can carry backdoors nobody tests for.
This is category context, not an independent assessment of ModelScan. Vendor-claimed differences are listed above. Assessment results appear only after examination.
Where to get more information
- Product website · github.com/protectai/modelscan
- Protect AI website
- Company listing
- Ask to be invited to review
- Claim this listing to add a supplier statement
Other products from Protect AI
- LLM Guard Claim
Deploy Bravely with the world’s most comprehensive AI security platform securing your AI agents, apps, models and data at every step. LLM Guard is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/llm-guard. Directory filing: Prompt-injection protection. Vendor legal name on this product record: Protect AI, Inc. LLM Guard is Protect AI's software product, from Protect AI, Inc. Published at github.com/protectai/llm-guard. Directory filing: Prompt-injection protection.
- Protect AI Platform Claim
Deploy Bravely with the world’s most comprehensive AI security platform securing your AI agents, apps, models and data at every step. Protect AI Platform is Protect AI's platform, from Protect AI, Inc. Published at protectai.com. Directory filing: AI security. Deployment options: SaaS and Private cloud / VPC. Vendor legal name on this product record: Protect AI, Inc. Protect AI Platform is Protect AI's platform, from Protect AI, Inc. Published at protectai.com. Directory filing: AI security. Deployment options: SaaS and Private cloud / VPC.
Why complete verification
Completing verification can improve the quality of the public evidence available on this product profile. Useful verified information can deepen the profile and make public questions about the named product more answerable. It does not buy directory ranking, review stars, a higher Assurance Score, a favourable certificate outcome, or a guaranteed Google ranking.
Payment remains independent from rankings and assessment outcomes. Start an assessment · Methodology