explainer

Databricks AI Security: Secure and Compliant AI Solutions

1,380 words, 64 clausesno date on the pageread 11/10/2026source

·Security & Trust Center

·Your data security is our top priority

·AI Security

·Best practices for mitigating the risks associated with AI models

·AI security refers to the practices, measures and strategies implemented to protect artificial intelligence systems, models and data from unauthorized access, manipulation or malicious activities. Organizations must implement robust security protocols, encryption methods, access controls and monitoring mechanisms to safeguard AI assets and mitigate potential risks associated with their use.

·The Databricks Security team works with our customer base to deploy AI and machine learning (ML) on Databricks securely with the appropriate features that meet customers' architecture requirements. We also work with dozens of experts internally at Databricks and in the larger ML and GenAI community to identify security risks to AI systems and define the controls necessary to mitigate those risks.

·Understanding AI systems

·What components make up an AI system and how do they work together?

·AI systems are composed of data, code and models. A typical end-to-end AI system has 12 foundational architecture components, broadly categorized into four major stages:

1Data operations include ingesting and transforming data and ensuring data security and governance. Good ML models depend on reliable data pipelines and secure infrastructure.
2Model operations include building custom models, acquiring models from a model marketplace or using software-as-a-service (SaaS) large language models (LLMs), such as OpenAI. Developing a model requires a series of experiments and a way to track and compare the conditions and results of those experiments.
3Model deployment and serving consists of securely building model images, isolating and securely serving models, automated scaling, rate limiting and monitoring deployed models.
4Operations and platform include platform vulnerability management and patching, model isolation and controls to the system and authorized access to models with security in the architecture. It also consists of operational tooling for CI/CD. It ensures the complete lifecycle meets the required standards by keeping the distinct execution environments - development, staging and production - secure for MLOps.

·The below image highlights the 12 components and how they interact across an AI system.

·Understanding AI security risks

·What are the security threats that may arise when adopting AI?

·In our analysis of AI systems, we identified 62 technical security risks across the 12 foundational architecture components. In the table below, we outline these basic components, which align with steps in any AI system, and highlight some examples of security risks. The full list of 62 technical security risks can be found in the Databricks AI Security Framework.

AI system stage	AI system components	Potential security risks
Data operations	1. Raw data 2. Data preparation 3. Datasets 4. Catalog and governance	20 specific risks such as: Insufficient access controls Missing data classification Poor data quality Lack of data access logs Data poisoning
Model operations	5. ML algorithm 6. Evaluation 7. Model build 8. Model management	15 specific risks such as: Lack of tracking and reproducibility of experiments Model drift Hyperparameters stealing Malicious libraries Evaluation data poisoning
Model deployment and serving	9. Model Serving - inference requests 10. Model Serving - inference responses	19 specific risks such as: Prompt inject Model inversion Denial of service (DOS) LLM hallucinations Black-box attacks
Operations and platform	11. ML operations 12. ML platform	8 specific risks such as: Lack of vulnerability management Lack of penetration testing and bug bounty Unauthorized privileged access Poor software development lifecycle (SDLC) Lack of compliance

·What controls are available for mitigating AI security risks?

·There are 64 prescriptive controls for mitigating the identified 62 AI security risks. These controls include:

·Cybersecurity best practices such as single sign-on, encryption techniques, library and source code controls and network access controls with a defense-in-depth approach to managing risks
·Data and AI governance-specific controls such as data classification, data lineage, data versioning, model tracking, data and model asset permissions and model governance
·AI-specific controls like model serving isolation, prompt tools, auditing and monitoring models, MLOps and LLMOps, centralized LLM management, fine-tuning and pretraining your models

·If you are interested in getting an in-depth overview of the security risks associated with AI systems and what controls should be implemented for each risk, we invite you to download our Databricks AI Security Whitepaper.

·Best practices for securing AI and ML models

·Data and security teams must actively collaborate to pursue their goal of improving AI systems' security. Whether you are implementing traditional machine learning solutions or LLM-driven applications, Databricks recommends taking the following steps as outlined in the Databricks AI Security Whitepaper. Identify the AI business use case

·Always remember your business goals. Ensure there is a well-defined use case with your stakeholders, whether already implemented or in the planning phases. We recommend leveraging Databricks Solution Accelerators, which are purpose-built guides to speed up results across your most common and high-impact AI and ML use cases. Determine the AI deployment model

·Choose an appropriate model such as a traditional custom tabular model, SaaS LLM, retrieval augmented generation (RAG), fine-tuned model or external model. Each deployment model has a varying shared responsibility split across the 12 AI system components and among your organization, the Databricks Data + AI Platform and any partners involved. Select the most pertinent risks

·From our documented list of 62 security risks, pinpoint the most relevant to your organization based on its deployment model. Enumerate threats for each risk

·Identify the specific threats linked to each risk and the targeted AI component for every threat. Choose and implement controls

·Select controls that align with your organization's risk appetite. The responsibility for the implementation of these controls may be shared among your organization, your cloud provider and your data and AI vendor(s). You can leverage the Databricks AI Security Framework compendium (Google Sheets, Excel) to help you map this out.

·FAQs

·What is Databricks' stance on responsible AI?

·As a data and AI company focused on helping enterprise customers extract value from their data to solve the world's toughest problems, we firmly believe that both the companies developing the technology and the companies and organizations using it must act responsibly in how AI is deployed. We conscientiously approach responsible AI across six key principles:

1Good governance is essential.
2AI should be democratized for all companies.
3Companies should own and control their data and models.
4AI is only as good as the data it is trained on, and enterprises should be able to control and monitor their data to help reduce hallucinations, bias and other errors.
5Enterprises should limit AI's environmental and financial costs to what is required to support their business objectives.
6Thoughtful regulation is needed to help ensure that AI is used responsibly.

·Check out this blog to learn more.

·How does Databricks ensure the security of AI models on its platform?

·What role does Databricks play in ensuring compliance with AI project data protection and privacy regulations?

·How can I contact the Databricks Security team for a workshop or to learn more about Databricks AI Security controls?

·Who is the Databricks AI Security Framework (DASF) intended for?

·AI Security Resources

·Databricks AI Security Framework (DASF)

·The Databricks Security team created the Databricks AI Security Framework (DASF) to address evolving vulnerabilities in AI systems with a holistic approach to mitigating risks beyond model security. View the DASF whitepaper Databricks AI Risk Workshop

·The Databricks Security team hosts AI risk workshops to help leaders understand AI systems, their risks and mitigation strategies.

·Contact us to participateView our flyer for more information AI Security Fundamentals Training

·This course explores the fundamentals of security in AI systems within the Databricks Data + AI Platform in five comprehensive modules.

·Take the one-hour course on Databricks Academy AI Security Events and Webinars

·Databricks security leaders regularly share expertise at events with industry leaders, enterprises, agencies and vendors. View our flyer for more information

·AI and ML Resources