Skip to content

AI Outlooks

News and viewpoints on the latest in AI security

Primary Menu
  • Home
  • What’s new in AI
    • AI Security News
    • Agentic AI News
    • AI Regulation News
    • AI Research News
    • AI Model News
  • Solutions
  • Cybersecurity
    • AI security
    • OWASP
    • Ransomware
    • Shadow AI
  • Learn
    • AI security
    • LLM security
    • AI governance
    • AI compliance
    • Agentic AI
    • AI infrastructure
    • AI data security
  • Home
  • News
  • Top AI security best practices
  • News

Top AI security best practices

Staff May 18, 2026

Most organizations get AI security wrong.

They focus on keeping sensitive data out of large language models. They guard against prompt injection. Meanwhile, the real exposure happens somewhere else entirely: at execution.

Here is what execution looks like. An AI agent with legitimate credentials opens a database, pulls a report, sends it through a processing pipeline, and forwards the output to a third-party integration. Every single step looks normal. The credentials are valid. The access patterns match expected behavior.

But somewhere in that chain, the agent’s instructions were altered. The data is now moving to a destination it should not reach. Traditional security tools see nothing wrong. They are watching who accessed what. Nobody is watching what the system actually did.

That gap is the difference between traditional security and AI security.

The surface-level concerns (data leakage into training sets, model theft, prompt injection) are real. But the harder problem is governing autonomous systems that operate inside your perimeter, using legitimate credentials, performing actions that look productive by design.

Quick orientation: the nine practices ahead

PracticeCore question it answersDifficulty
1. AI bill of materialsWhat do we even have?Low
2. API and endpoint securityHow do things connect?Low
3. Zero trust and least privilegeWho can do what?Medium
4. Poisoning and adversarial defenseIs our model being manipulated?High
5. Behavioral monitoringWhat are our systems actually doing?High
6. Third-party vettingCan we trust our dependencies?Medium
7. Data encryption and privacyWhere does sensitive data go?Medium
8. Governance and accountabilityWho is responsible when something fails?Medium
9. Employee trainingDo our people know what not to do?Low

Why traditional security misses the point with AI

Traditional cybersecurity answers three questions: Who accessed the system? From where? What data did they touch?

That model works when humans are the actors. A login at 3 a.m. from an unrecognized location triggers an alert for a reason.

AI agents do not fit that model.

They log in from expected IP ranges. During business hours. Using provisioned service accounts. They access exactly the systems they were configured to access. The anomaly is not in the access pattern. It is in the sequence of actions, the combination of operations, the emergent behavior that no individual log entry captures.

Human threat vs AI threat: What monitoring catches

Signal typeHuman attackerAI agent compromise
Unusual login timeCommon, triggers alertRare, looks normal
Unfamiliar IPCommon, triggers alertRare, uses expected ranges
Unauthorized data accessDetected by access controlsUses legitimate credentials
Suspicious sequence of actionsOften noisy or obviousBlends into normal operations
Volume anomalyCould indicate exfiltrationCould indicate abuse, but looks like legit usage

The NIST AI Risk Management Framework, released in January 2023 and updated with additional guidance in 2024, was one of the first major standards to explicitly call out this gap. It recommends mapping AI system behavior across the full lifecycle rather than auditing discrete access events. MITRE ATLAS, the adversarial threat landscape framework for AI systems, catalogs tactics and techniques that exploit exactly this blind spot: attackers coercing AI systems into actions that blend into normal operations.

If your AI security strategy starts and ends with access control and data classification, you are defending against yesterday’s threat model.


1. Build an AI bill of materials before anything else

You cannot secure what you cannot see.

That principle applies to AI with more urgency than most teams realize.

An AI bill of materials (AI-BOM) is an inventory of every component that touches your AI systems:

  • Models (production, staging, development)
  • Training datasets and fine-tuning data
  • Inference pipelines
  • Embedding services and vector databases
  • API integrations
  • Third-party libraries and their dependencies

Most organizations, when they first build one, discover components they did not know were connected to AI workflows.

A model card is the documentation layer that sits on top of the AI-BOM. For each model, it records:

  • What the model does
  • What data it was trained on
  • Known limitations
  • Security requirements
  • Who is responsible for it

Without model cards, your inventory is just a list of names. With them, it becomes something your security team can act on.

Building your first AI-BOM

Start by cataloging every model across production, development, and staging environments. Expect this to take three to five days if someone knows where everything lives.

Then map each model’s dependencies — frameworks, libraries, data sources, and external APIs. That is another five to eight days.

Next, identify which identities (human and service accounts) have access to each component, which should take three to five days.

Finally, create a model card for each model documenting its purpose, data provenance, and security posture. Budget one to two days per model for this.

Aim for completeness over perfection on the first pass.

A partial inventory with a few gaps is actionable. No inventory at all means you are flying blind. Teams that skip this end up finding out about shadow deployments during incidents, not audits.


2. Secure APIs, endpoints, and model access points

AI models do not sit in isolation. They are exposed through APIs, embedded in applications, and connected to data pipelines that stretch across cloud boundaries.

Each connection point is an attack surface.

The four API security layers most teams skip

Layer 1: Authentication. API keys are not enough. Use OAuth 2.0 tokens with short lifetimes. Rotate credentials on a schedule that assumes compromise. A leaked API key valid for six months is a gift to an attacker.

Layer 2: Input validation. Do not pass raw user input directly to a model. Sanitize it. Validate schema conformance. Reject anything that does not match expected formats. Model inference endpoints should never be the first line of input validation.

Layer 3: Rate limiting. Apply it at multiple levels. A single misconfigured client should not be able to exhaust your inference capacity. Rate limiting protects availability and makes abuse more expensive.

Layer 4: Network isolation. If a model does not need to be reachable from the public internet, it should not be. Configure private network endpoints for model serving infrastructure. Route traffic through your existing network security controls.

API keys exposed in client-side code can be scraped and abused within minutes. This is not unique to any single provider. It happens across every model service.

The fix is not a better API key. The fix is never putting keys where they can be scraped.


3. Lock down authentication with zero trust and least privilege

AI systems interact with data stores, internal services, and external APIs. Each interaction happens through an identity.

Each identity should have exactly the permissions it needs and nothing more.

Role-based access control (RBAC) is the starting point, not the destination.

Identities in a typical AI pipeline and what they need

IdentityShould accessShould never access
Training job service accountCurated training data bucketModel registry (write)
Inference endpoint identityModel weights (read)Training data
Data preprocessing workerRaw data staging areaProduction inference endpoints
Monitoring agentLogs and metricsModel weights or training data

When a training job that should only read from a curated dataset bucket suddenly attempts to write to a model registry, that should fail by default. Not because someone remembered to check, but because the permission was never granted.

Multi-factor authentication (MFA) should apply to every human accessing AI infrastructure. For service accounts, use managed identities where your cloud provider supports them. This eliminates static credentials entirely.

The zero-trust principle matters more for AI than for most workloads. An AI agent operating under a compromised identity can chain together legitimate API calls in ways that produce illegitimate outcomes. If each step in that chain requires explicit, scoped authorization, the blast radius shrinks to a single operation instead of an entire workflow.

A practical rule: if you cannot explain, in one sentence, exactly what permissions a given service account has and why, it has too many.


4. Defend training pipelines against data poisoning and adversarial inputs

Data poisoning does not announce itself.

An attacker introduces a small number of crafted examples into a training dataset (sometimes as few as a few hundred samples in a corpus of millions). The model learns a behavior the attacker controls. The behavior might activate only under specific input conditions, making it invisible during normal testing.

Adversarial inputs work differently. They target inference time rather than training time. A stop sign with carefully placed stickers makes a vision model see a speed limit sign. A block of text with strategically inserted characters makes a language model produce a specific, unintended output.

Both attacks exploit the same underlying vulnerability: models learn correlations from data, and those correlations can be manipulated.

Data poisoning vs adversarial attacks at a glance

Data poisoningAdversarial attacks
WhenTraining timeInference time
HowContaminated training dataCrafted inputs to deployed model
VisibilityInvisible during normal testingVisible in model output
DetectionStatistical checks on training dataInput sanitization + output monitoring
PreventionData provenance validationAdversarial training + preprocessing

Defense strategies across both attack types:

  • Validate dataset provenance. Know where every training dataset came from and who had access to it before it reached your pipeline.
  • Run statistical checks on training data distributions before ingestion. A sudden change in label distribution or feature values can signal tampering.
  • Implement adversarial training. Generate attack examples during development and include them in your training set so the model learns to recognize manipulation attempts.
  • Preprocess inference inputs through sanitization layers. Strip or neutralize known attack patterns before they reach the model.

None of these defenses is perfect on its own. Deployed together, they raise the cost of a successful attack from trivial to expensive. That is often the difference between being targeted and being ignored.


5. Monitor what your AI actually does, not just what it accesses

This is where most security programs fall short.

Traditional monitoring answers: did someone access the customer database?

AI monitoring needs to answer: did the agent that accessed the customer database then send that data somewhere unexpected?

The access itself was legitimate. The sequence of subsequent actions is where the risk lives.

What to monitor across the AI stack

LayerWhat to watch forTool category
Model inputs and outputsDistribution shifts that suggest manipulationDrift detection
AI agent API call sequencesPatterns that deviate from established baselinesBehavioral analytics
Resource consumptionAnomalies suggesting resource jacking (crypto mining, unauthorized training)Infrastructure monitoring
Data movement across trust boundariesLegitimate-looking transfers to unexpected destinationsData flow analysis

Anomaly detection is useful here, but behavioral baselining matters more.

You need to know what normal looks like before you can recognize abnormal. For an AI agent that typically processes 50 transactions per hour during business hours, 2,000 transactions at 3 a.m. is worth investigating, even if every transaction succeeds.

Static analysis looks at code. Runtime observes what the code actually does when it executes. Most security programs are strongest at the layers that matter least for AI.


6. Vet every third-party component

AI development depends on open-source models, community frameworks, pre-trained weights, and third-party datasets.

Each dependency is a potential entry point.

The risk is not hypothetical. Pre-trained models downloaded from public repositories can carry unexpected behavior. Malicious weights can be embedded in model files. Third-party datasets can contain poisoned samples that influence model outputs in ways that only surface under specific conditions.

Vetting third-party components means:

  • Checking provenance of pre-trained models. Where did the weights come from? Who trained them? On what data?
  • Running dependency scans on AI frameworks and libraries, the same way you scan application dependencies for CVEs
  • Testing model files for embedded code before loading them into any environment with network access
  • Maintaining an allowlist of approved model sources and blocking imports from unvetted repositories

Third-party component vetting checklist

Component typeRiskVerification stepTooling
Pre-trained modelsEmbedded malicious codeTest model files before loadingModel scanning tools
AI frameworks and librariesKnown CVEsRun dependency scans (same as app deps)SCA scanners
Training datasetsPoisoned or biased dataValidate provenance and distributionStatistical profiling
Model weights from public reposBackdoor weightsVerify source and integrity hashCryptographic verification

Open-source AI accelerates development. Blocking it entirely is not practical for most teams. The alternative is treating external AI components with the same scrutiny you apply to any other software supply chain: automated scanning, provenance verification, and runtime isolation.


7. Encrypt, anonymize, and control sensitive data

AI systems consume data. Some of that data is sensitive.

Customer records. Proprietary code. Internal communications. Financial projections.

Every place data pauses or passes through is a place it can leak.

Encryption is table stakes. Data at rest should be encrypted. Data in transit should be encrypted. But encryption alone is not enough.

AI models can memorize and later reproduce training data. In 2021, researchers demonstrated that large language models can regurgitate verbatim training examples under certain prompting conditions, including personally identifiable information (Carlini et al., USENIX Security 2021.

Privacy preservation techniques compared

TechniqueWhat it doesStrengthLimitation
Encryption (at rest/in transit)Prevents unauthorized access to stored/moving dataStrongDoes not prevent model memorization
Differential privacyAdds calibrated noise, making it mathematically infeasible to identify individual recordsFormal guaranteeMay reduce model accuracy slightly
Role-based access controlsLimits which identities can access which datasetsOperationalDoes not protect against authorized users misusing data
Data loss prevention (DLP)Catches sensitive data in prompts and responses before it leavesFast, practicalCan miss novel sensitive data patterns
Regular auditsConfirms what data each model can access and whether access is justifiedCatches drift over timeRequires manual effort

If an employee pastes a customer list into a model prompt, DLP should block it. If a model is memorizing training data, differential privacy makes extraction infeasible. If permissions have drifted over six months, an audit catches it.

No single technique solves the problem. The combination does.


8. Establish governance before regulators force your hand

AI regulation is not coming. It is here.

The EU AI Act entered into force in August 2024, with obligations for high-risk AI systems phasing in over 2025 through 2027. NIST continues to update the AI Risk Management Framework with sector-specific profiles. ISO/IEC 5338 and ISO/IEC 27090 (under development for AI security) are the two most relevant international standards.

Organizations that build governance frameworks now will spend 2026 adjusting controls. Organizations that wait for enforcement actions will spend 2026 scrambling.

The minimum viable governance program

ComponentWhat it meansWho owns it
Current AI inventoryUpdates to the AI-BOM whenever a model is added, changed, or retiredML engineering lead
Audit trails for AI decisionsLog inputs, outputs, and model version for every consequential decisionSecurity engineering
Named accountable person per systemSomeone who can answer “why did this system do that?” and has the authority to pull it offlineSystem owner (not the model)
Regular review cadenceReviews tied to model updates, regulatory changes, and incident post-mortemsGRC team

Explainable AI techniques help, but the minimum bar is logging inputs, outputs, and model version for every consequential decision.

When a model denies a loan, flags a transaction, or routes a patient to a specific treatment path, someone needs to be able to trace why.

Governance is not a one-time project. The frameworks (NIST RMF, ISO standards, the EU AI Act) provide the scaffolding. Your job is to put walls on it that correspond to what your AI systems actually do.


9. Train every employee, not just the security team

Shadow AI is the fastest-growing category of AI risk in most organizations.

The term describes employees using AI tools without the security team’s knowledge or oversight. This is the core of what we call shadow AI. Managed AI services are now widespread across organizations of all sizes, but many security teams still cannot enumerate which AI tools their employees are actively using.

Real examples of what employees do:

  • Paste proprietary code into public chatbots for debugging help
  • Upload customer contracts to summarize with AI
  • Connect personal AI accounts to work data without changing default privacy settings

Each of these is well-intentioned. Each creates exposure.

AI security training: what every employee needs to know

TopicThe message
Approved toolsThese are the AI tools you can use, and here is why the approval process exists
Forbidden dataNever enter these categories of data into a public AI service
Privacy settingsHere is how to check whether an AI tool’s default settings expose company data
ReportingHow to report suspected AI misuse (without fear of punishment)

Policy should be clear, short, and enforced.

A 15-page AI usage policy that nobody reads is worse than a one-page policy that everyone knows. Make the rules obvious. Make the enforcement visible. The shadow AI problem shrinks from a crisis to a manageable risk.


What these practices cost in time and resources

Nobody talks about cost in AI security articles. That is why most teams start three practices and finish none.

Effort and resource estimates

PracticeEffortTeam neededCost tierStart this quarter?
AI-BOM2-4 weeks initialSecurity + ML engineering (2-3 people PT)LowYes
API/endpoint security1-2 weeks per integrationPlatform engineeringLowYes
Zero trust + least privilege4-8 weeks, phased rolloutIdentity + platform teamsMediumYes, phased
Data poisoning defenses6-12 weeks for pipeline integrationML engineering + securityHighRoadmap
Behavioral monitoring8-16 weeks for baseline + tuningSecurity operations + ML engineeringHighRoadmap
Third-party vetting2-4 weeks for processSecurity + procurementMediumYes
Data privacy (diff. privacy + DLP)4-8 weeks depending on data volumeData engineering + securityMediumYes
Governance framework6-12 weeks initialGRC + legal + securityMediumYes
Employee training2-4 weeks for materialsSecurity awareness + L&DLowYes

Which practices to start with, by team size and maturity

If you have…Start hereAdd next quarter
No AI security programAI-BOM + API securityTraining + third-party vetting
Basic visibility, no monitoringBehavioral monitoringData privacy + governance
Monitoring in place, weak governanceGovernance frameworkData poisoning defenses

Practices 1, 2, and 9 can start this quarter with existing staff and minimal budget. Practices 4 and 5 require dedicated engineering time. Plan them into the roadmap rather than attempting them as side projects.


How priorities shift by organization size

The same nine practices apply regardless of size. But the order of operations changes.

Startup (under 50 people, fewer than 5 AI models in production)

Start with practice 1 (AI-BOM) and practice 2 (API security). You need to know what you have, and you need to secure how it connects to everything else. Practices 8 and 9 (governance and training) should follow within the first year. Advanced monitoring and differential privacy can wait until you have something worth stealing.

Midmarket (50-500 people, 5-25 AI models)

Practices 1 through 4 are table stakes. You should not be deploying without them. Practices 5 (behavioral monitoring) and 6 (third-party vetting) become critical as your attack surface grows with each new integration. Practice 8 (governance) starts becoming a customer requirement, especially if you sell to enterprises.

Enterprise (500+ people, 25+ AI systems)

All nine practices apply with equal urgency. The difference is scale. An AI-BOM at enterprise scale is a program, not a document. Behavioral monitoring requires dedicated headcount. Governance needs to satisfy regulators, auditors, and customers with conflicting requirements. The practices do not change, but the cost of skipping any one of them compounds across the organization.


The regulations shaping AI security

AI security regulation is moving faster than most teams’ compliance programs.

Regulation / FrameworkStatusWho it affectsKey deadline
EU AI ActIn force (Aug 2024)Any org with AI systems touching EU usersHigh-risk obligations phase in 2025-2027
NIST AI RMFVoluntary, but becoming de facto standardU.S. orgs, especially those selling to government/enterpriseSector-specific profiles coming (critical infrastructure first, 2026)
ISO/IEC 27090 + 53385338 published 2023; 27090 under developmentInternational compliance programsTimeline TBD; early alignment via OWASP AI Exchange
CISA AI Data Security GuideReleased May 2025Defense industrial base, critical infrastructureAvailable now; recommendations apply broadly

EU AI Act. In force since August 2024. High-risk AI system obligations (risk management, data governance, transparency, human oversight) phase in over 2025-2027. Fines reach the higher of EUR 35 million or 7% of global annual turnover. If your AI systems touch EU users, this applies to you regardless of where your company is based.

NIST AI RMF. Voluntary today. But it is becoming the standard that U.S. regulators, auditors, and enterprise customers reference. NIST released a concept note in April 2026 for a profile on trustworthy AI in critical infrastructure. More sector-specific profiles are coming. Organizations that map their controls to NIST RMF now will have an easier time adapting to whatever follows.

ISO/IEC standards. ISO/IEC 5338 (AI system life cycle processes) was published in 2023. ISO/IEC 27090 (AI security) is under development, with OWASP contributing content directly through its AI Exchange. Once 27090 is published, these will become the baseline that international compliance programs reference.


Frequently asked questions

How is AI security different from traditional cybersecurity?

Traditional cybersecurity focuses on perimeter defense, access control, and data protection.

AI security adds behavioral monitoring at execution: watching what AI systems do with the access they have, not just controlling who gets through the door.

An AI agent with legitimate credentials can chain together operations that produce harmful outcomes. No access log will flag the sequence as anomalous unless you are specifically monitoring for it.

What is an AI bill of materials and why does it matter?

An AI-BOM is an inventory of every component in your AI pipeline: models, datasets, frameworks, APIs, and dependencies. You need one because you cannot secure what you do not know exists. Most organizations discover shadow AI deployments and undocumented data connections when they build their first AI-BOM.

What are adversarial attacks and how do they differ from data poisoning?

Data poisoningAdversarial attacks
TimingDuring trainingDuring inference
MethodContaminate datasetCraft deceptive input
GoalModel learns attacker-controlled behaviorModel produces wrong output
AnalogyTainting the water supplyHanding someone a map to the wrong destination

Why are APIs the most common attack vector for AI systems?

AI models are almost never accessed directly. They sit behind APIs.

APIs expose authentication tokens, rate limits, input validation, and authorization logic. Every one of those layers can be misconfigured. Attackers scan for exposed API keys because those keys give them exactly the same access your application has. Once inside, they can query models at scale, extract training data through repeated prompting, or pivot to other services the model connects to.

What role does NIST play in AI security standards?

NIST’s AI Risk Management Framework is the most widely referenced AI security standard in the United States.

It is voluntary. But it shapes how regulators, auditors, and enterprise procurement teams evaluate AI systems. NIST also publishes adversarial machine learning guidance and has signaled that sector-specific AI RMF profiles are coming, starting with critical infrastructure.

Which best practice should an organization implement first?

Build an AI-BOM.

You need to know what AI systems you have, where they run, what data they access, and who is responsible for them before you can effectively secure any of it. The AI-BOM is not the most exciting practice on this list. It is the one that makes every other practice possible.

How often should AI security practices be reviewed?

Practice areaReview frequencyTriggered by
AI-BOM and access controlsQuarterlyNew model deployment
Governance frameworksWhen regulations changeNew model types deployed
Adversarial testingBefore every major model releaseMaterial change to training data or architecture
Monitoring baselinesContinuouslySystem behavior evolution

Where to go from here

Pick one practice and ship it this month.

The AI-BOM is the obvious starting point. It creates the visibility that every subsequent practice depends on. If you already have one, move to API and endpoint security. If you have both, start on behavioral monitoring. That is where most teams discover problems they did not know they had.

The gap between having an AI security strategy and having one that actually works is not about the number of practices you adopt. It is about whether you are watching what your AI systems do or just what they access. The organizations that get this right stop treating AI like another application workload and start treating it like an autonomous decision-maker operating inside their perimeter.

For autonomous agents specifically, the practices tighten into 12 agentic AI security controls you can verify by artifact.

Continue Reading

Previous: Cloudflare vs Akamai on AI security
Next: What is AI data poisoning?

More in AI security

  • Guide

The agentic AI security checklist: 12 controls to verify before you deploy

Staff September 4, 2026
Twelve controls to verify before you deploy an AI agent, each mapped to an OWASP ASI risk...
Read more Read more about The agentic AI security checklist: 12 controls to verify before you deploy
LLM jailbreak defense: techniques that actually stop attacks Jailbreak defense
  • Cybersecurity

LLM jailbreak defense: techniques that actually stop attacks

Staff July 28, 2026
How do enterprises secure AI data pipelines at production scale? safety
  • Cybersecurity

How do enterprises secure AI data pipelines at production scale?

Staff July 28, 2026
How companies can defend against AI model extraction attacks
  • Guide

How companies can defend against AI model extraction attacks

Staff July 23, 2026
What is a model inversion attack?
  • Glossary

What is a model inversion attack?

Staff July 22, 2026

Glossary

model router
  • LLMs

What is a model router for AI? A plain-English guide

Staff July 30, 2026
A model router for AI is a decision layer that picks which large language model answers each...
Read more Read more about What is a model router for AI? A plain-English guide
What is agentic SDLC?
  • Glossary

What is agentic SDLC?

Staff July 22, 2026
What is a model inversion attack?
  • Glossary

What is a model inversion attack?

Staff July 22, 2026
LLM system prompt leakage: what it is, how it works, and how to stop it agentic ai
  • Glossary

LLM system prompt leakage: what it is, how it works, and how to stop it

Staff July 15, 2026
What is LLM supply chain security? (OWASP LLM03:2025 explained) llm supply chain
  • Glossary

What is LLM supply chain security? (OWASP LLM03:2025 explained)

Staff July 14, 2026

Guides

The agentic AI security checklist: 12 controls to verify before you deploy
  • Guide

The agentic AI security checklist: 12 controls to verify before you deploy

Staff September 4, 2026
LLM jailbreak defense: techniques that actually stop attacks Jailbreak defense
  • Cybersecurity

LLM jailbreak defense: techniques that actually stop attacks

Staff July 28, 2026
How do enterprises secure AI data pipelines at production scale? safety
  • Cybersecurity

How do enterprises secure AI data pipelines at production scale?

Staff July 28, 2026
How companies can defend against AI model extraction attacks
  • Guide

How companies can defend against AI model extraction attacks

Staff July 23, 2026
What is a model inversion attack?
  • Glossary

What is a model inversion attack?

Staff July 22, 2026
How to prevent adversarial attacks on AI models
  • Guide

How to prevent adversarial attacks on AI models

Staff July 22, 2026
  • Home
  • What’s new in AI
  • Solutions
  • Cybersecurity
  • Learn
Copyright © All rights reserved. | by AF themes.