Company · Directory listing
Center for AI Safety
Reducing societal-scale risks from AI by advancing safety research, building the field of AI safety researchers, and promoting safety standards. Center for AI Safety publishes HarmBench as named AI products. Center for AI Safety is used for Red teaming work. Center for AI Safety is recorded in United States. Center for AI Safety publishes product information at safe.ai.
Center for Artificial Intelligence Safety, Inc.
United States · US · 1 listing
Customer review aggregate: No published reviews
Ranking status: Directory only — not ranked
Directory ranking uses customer-review stars only. The separately purchased assurance assessment records Bronze/Silver/Gold depth, Assurance Score and risk class; none affects directory position.
Company details
About Center for AI Safety
Reducing societal-scale risks from AI by advancing safety research, building the field of AI safety researchers, and promoting safety standards. Center for AI Safety publishes HarmBench as named AI products. Center for AI Safety is used for Red teaming work. Center for AI Safety is recorded in United States. Center for AI Safety publishes product information at safe.ai.
- Legal name
- Center for Artificial Intelligence Safety, Inc.
- Headquarters
- United States
- Markets
- —
- Company size
- —
Directory & rankings
Customer ranking
Directory only. This listing has no customer stars or ranked position.
- Red teaming · Directory only · Free listing · ranking code packs from £200 ex VAT
0 customer relationships verified at V3+ · Trustmark assessment results never affect this order.
Listings
Products and services from Center for AI Safety
One product is listed for this company. Functional classification, deployment and autonomy are descriptive attributes. Impact class remains a separate assurance result.
- Public JSON for website embeds
HarmBench
From their website · not verified evidence
SOFTWARE PRODUCT · Red teaming · AI Safety & Security
- Sectors
- Not specified
- Deployment
- Not specified
- Capabilities
- Not specified
- Autonomy
- ASSISTIVE
- Data exposure
- Not specified
What the vendor’s website says · supplier-provided, not verified evidence
Center for AI Safety. Reducing societal-scale risks from AI by advancing safety research, building the field of AI safety researchers, and promoting safety standards. HarmBench is Center for AI Safety's software product, from Center for Artificial Intelligence Safety, Inc. Published at github.com/centerforaisafety/HarmBench. Directory filing: Red teaming. Vendor legal name on this product record: Center for Artificial Intelligence Safety, Inc. HarmBench is Center for AI Safety's software product, from Center for Artificial Intelligence Safety, Inc. Published at github.com/centerforaisafety/HarmBench. Directory filing: Red teaming.
Verified claims
- Domain associated with this organisation: Yes
- Claim status: UNCLAIMED
- Last verified: 2026-09-17
What we have not verified
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.
The organisation description above is supplier-provided unless a specific statement is listed as verified.
Products assessed
No assessed products are listed on this profile yet.
Customer experience
No published reviews yet. Review screenshots appear only with a qualifying Verity review; directory thumbnails from a vendor website are not review evidence.
Customer stories
No consented, relationship-verified customer stories yet.
FAQs
What does Center for AI Safety do?
Reducing societal-scale risks from AI by advancing safety research, building the field of AI safety researchers, and promoting safety standards. Center for AI Safety publishes HarmBench as named AI products. Center for AI Safety is used for Red teaming work. Center for AI Safety is recorded in United States. Center for AI Safety publishes product information at safe.ai.
What AI services or products does it provide?
HarmBench
Which AI categories does it operate in?
Red teaming
Has Center for AI Safety been independently assessed by AI TrustMark?
No independent assessment result is published. Current listing status: Directory listing.
What procurement or assurance information is available?
Company identity, category assignment and any published certificates or assessment summaries appear on this page. Absence of a field means it has not been evidenced here.
Last verified: 2026-09-17
Methodology version: See current methodology
Why complete verification
Completing verification can improve the quality of the public evidence available on this supplier 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