10 realistic exam questions, graded as you go, with the exact rule or statute citation for every answer. Start free, no sign-up.
Timed mock exam
12 questions in 14 minutes, drawn from every topic. No answers shown until the end, then a full score breakdown, your weakest topics and a review of what you missed.
Prices are in US dollars, plus tax where it applies. Stripe, our payment processor, calculates tax at checkout.
All sales are final. If something is really wrong, such as a duplicate charge or a purchase that does not unlock what you bought, write to support@careerexampro.com and we will put it right.
One-time payment. Nothing renews.
You have an exam ticket for this practice test. Start the timed mock exam to use it.
Exam Snapshot & Official Blueprint
Official Exam Fee
$575–$760 (ISACA member / non-member)
Format & Time Limit
90 MCQs · Computer-Based Testing (PSI)
Passing Standard
Scaled score 450 out of 800
Typical Prep Incumbents
$900–$1,600+ (ISACA official review kits — sparse third-party Q-banks)
Official Domain Breakdown
Exam Domain
Weight
AI Governance, Policy & Enterprise Program Management
34%
AI Risk Management, Bias, Drift & Third-Party Vendor Controls
33%
AI Technologies, Security Controls & Algorithmic Assurance Auditing
33%
High-Yield Formulas, Statutes & Rules Cheat Sheet
Prerequisites: AAISM requires an active CISM or CISSP; AAIA requires an active CISA (or recognized audit credential like CIA/CPA in an IT audit role).
Third-Party Foundation Model Governance (AAISM): Verify Zero Data Retention (ZDR) API agreements, no-training clauses, sub-processor lists, model-version pinning, and incident notification SLAs.
Frequently Asked Questions
What is the difference between ISACA AAISM and AAIA?
AAISM focuses on managing enterprise AI security programs and risk (for CISM/CISSP holders), while AAIA focuses on independent assurance and auditing of AI pipelines and governance (for CISA/CIA/CPA holders).
Exact question counts, passing scores, and allowed reference materials vary by testing window and state/agency. Always confirm current rules with the official testing provider.
Sample questions
API telemetry shows an external B2B tenant sending 1.8 million systematically spaced synthetic feature vectors to a proprietary fraud-scoring endpoint over 48 hours, recording full floating-point class probabilities for every response. Which AI threat is most likely in progress, and which API control reduces risk without breaking legitimate customer scoring?
Indirect prompt injection through transaction memos; mitigate by stripping special characters from string fields and adding a static system prompt wrapper.
Vector database embedding inversion; mitigate by rotating index encryption keys and migrating embeddings from cosine similarity to Euclidean distance.
Model extraction to build a surrogate replica; return coarse labels or rounded scores, apply rate limits, and flag query anomalies.
Concept drift caused by seasonal spending shifts; mitigate by scheduling automated nightly model retraining on the incoming synthetic API payloads.
Show the answer
C. Model extraction to build a surrogate replica; return coarse labels or rounded scores, apply rate limits, and flag query anomalies.
High-volume, systematically distributed probing combined with collecting exact floating-point confidence vectors enables model extraction (stealing a functionally equivalent surrogate model). Truncating precision to coarse bands or binary decisions, throttling tenants, and detecting abnormal query distributions significantly slow extraction.
An MLOps CI/CD runner pulls third-party open-weights checkpoints in legacy PyTorch .pkl/.pt format from a community model hub and deserializes them directly inside a GPU container attached to a broad production IAM role. What is the primary supply-chain vulnerability, and what MLSecOps standard prevents exploitation?
Arbitrary code execution via pickle deserialization; mandate SafeTensors, verify signatures, scan artifacts, and load in least-privilege sandboxes.
GPU side-channel memory leakage across virtual machines; mandate single-tenant bare-metal instances and disable CUDA shared-memory caching inside all build runners.
Gradual weight quantization loss across container rebuilds; mandate FP32 precision exports and archive intermediate optimizer checkpoints in immutable object storage.
Unintended hallucination of deprecated library APIs; mandate deterministic decoding with temperature zero and enable automated unit-test retries in CI/CD.
Show the answer
A. Arbitrary code execution via pickle deserialization; mandate SafeTensors, verify signatures, scan artifacts, and load in least-privilege sandboxes.
Python pickle files execute embedded deserialization routines (such as __reduce__) upon loading, allowing malicious model weights to run arbitrary shell commands with the container's IAM privileges. Enforcing non-executable formats like SafeTensors, verifying cryptographic hashes/signatures, and isolating model loaders with least privilege eliminates this attack path.
Reference: CompTIA SecAI+ (CY0-001) / OWASP Top 10 for LLM Applications (LLM03: Supply Chain)
Secure Web Gateway (SWG) and CASB telemetry reveal that 42% of software engineers are pasting proprietary source code and customer incident logs into consumer generative AI web apps under personal logins. Which remediation approach best controls Shadow AI while sustaining developer velocity?
Issue an immediate policy banning all generative AI tools enterprise-wide and revoke local administrator rights without offering any approved technical substitute.
Block unsanctioned AI apps via SWG/CASB DLP and provide an enterprise AI gateway featuring PII/secret redaction, audit logging, and zero-data-retention APIs.
Deploy endpoint keyloggers across engineering laptops to record pasted prompts and forward weekly compliance reports to department managers for manual review.
Allow consumer web apps over corporate Wi-Fi while relying exclusively on annual acceptable-use training acknowledgments to deter proprietary code uploads.
Show the answer
B. Block unsanctioned AI apps via SWG/CASB DLP and provide an enterprise AI gateway featuring PII/secret redaction, audit logging, and zero-data-retention APIs.
Outright bans without a sanctioned alternative drive Shadow AI underground to personal devices and cellular networks. Combining CASB/SWG discovery and blocking of unsanctioned endpoints with an approved enterprise LLM gateway (providing DLP redaction, centralized logging, and ZDR agreements) resolves data-leakage risk sustainably.