AIUC-1
Context
IntroductionCertificate overview
Framework comparisons
ChangelogAIUC-1 ConsortiumProvide input on AIUC-1Contact
Standard
A. Data & Privacy
B. Security
Third-party testing of adversarial robustnessDetect adversarial inputManage public release of technical detailsPrevent AI endpoint scrapingImplement real-time input filteringPrevent unauthorized AI agent actionsEnforce user access privileges to AI systemsProtect AI system deployment environmentLimit output over-exposure
C. Safety
D. Reliability
E. Accountability
F. Society
Certification
AIUC-1 certification Scoping Accredited auditors FAQ
Evidence overview
AIUC-1

Share your details and let us know how you hope to use AIUC-1

I am interested in...

The Security, Safety, and Reliability standard for AI agents

Stay up to date with AIUC-1

AIUC-1
AIUC-1.COM

© 2026.AIUC

OverviewChangelogConsortium

LEGAL

Privacy PolicyTerms of Service
AIUC-1 Standard
→
B. Security
→
B009. Limit output over-exposure
B009

Limit output over-exposure

Implement output limitations and obfuscation techniques to safeguard against information leakage

Keywords

Output ObfuscationFidelity ReductionInformation LeakageAdversarial UseResponse Filtering

Application

Mandatory

Frequency

Every 12 months

Type

Preventative

Crosswalks

MITRE ATLAS
AML-M0002: Passive AI Output Obfuscation
NIST AI RMF
MEASURE 2.10: Privacy risk assessment
OWASP Top 10
LLM02:25 - Sensitive Information Disclosure
LLM05:25 - Improper Output Handling
LLM08:25 - Vector and Embedding Weaknesses
LLM09:25 - Misinformation
CSA AICM
AIS-09: Output Validation
IBM AI Risk Atlas
IBM 47: Inference - Prompt leaking
IBM 74: Output - Revealing confidential information
Cisco AI Security Framework
AITech-4.2: Context Boundary Attacks
AITech-8.1: Membership Inference
AITech-8.2: Data Exfiltration / Exposure
AITech-8.3: Information Disclosure
AITech-8.4: Prompt/Meta Extraction
AITech-10.2: Model Inversion
AITech-12.2: Insecure Output Handling

Control activities

Typical evidence

Reducing or limiting the number of results shown in outputs to relevant only to balance security and utility. For example, character limits, limits on inference time.
B009.1 Config: Output volume limits

Code or configuration implementing output restrictions - may include character or token limits, inference time limits, result count restrictions, or timeout configurations preventing excessive output. Can be demonstrated by product demo showing system timeout when requesting output exceeding limits.

Category

Technical Implementation
Engineering CodeProduct
Text-generationVoice-generation
Providing user-facing notices or documentation about output limitations.
B009.2 Demonstration: User output notices

Product interface showing user notices about output limitations - may include messages indicating truncated or suppressed outputs for security or privacy reasons, user documentation explaining limitation policies, or help articles describing output restrictions.

Category

Operational Practices
Product
Text-generationVoice-generation
Limiting the fidelity of model outputs in certain use cases. For example, applying output rounding, threshold bands, or obfuscation techniques to reduce the risk of model inversion.
B009.3 Config: Output precision controls

Code implementing output fidelity limitations - may include rounding logic for numerical outputs, threshold bands reducing precision, or obfuscation techniques preventing model inversion, precision-sensitive data disclosure, or adversarial model extraction attacks.

Category

Technical Implementation
Engineering Code
Text-generationVoice-generation

Organizations can submit alternative evidence demonstrating how they meet the requirement.

AIUC-1 is built with industry leaders

Phil Venables

"We need a SOC 2 for AI agents— a familiar, actionable standard for security and trust."

Google Cloud
Phil Venables
Former CISO of Google Cloud
Dr. Christina Liaghati

"Integrating MITRE ATLAS ensures AI security risk management tools are informed by the latest AI threat patterns and leverage state of the art defensive strategies."

MITRE
Dr. Christina Liaghati
MITRE ATLAS lead
Hyrum Anderson

"Today, enterprises can't reliably assess the security of their AI vendors— we need a standard to address this gap."

Cisco
Hyrum Anderson
Senior Director, Security & AI
Prof. Sanmi Koyejo

"Built on the latest advances in AI research, AIUC-1 empowers organizations to identify, assess, and mitigate AI risks with confidence."

Stanford
Prof. Sanmi Koyejo
Lead for Stanford Trustworthy AI Research
John Bautista

"AIUC-1standardizes how AI is adopted. That's powerful."

Orrick
John Bautista
Partner at Orrick
Lena Smart

"An AIUC-1certificate enables me to sign contracts much faster— it's a clear signal I can trust."

SecurityPal
Lena Smart
Head of Trust for SecurityPal and former CISO of MongoDB