OWASP AI Security and Privacy Guide
This page is the OWASP AI security & privacy guide. It has two parts:
Artificial Intelligence (AI) is on the rise and so are the concerns regarding AI security and privacy. This guide is a working document to provide clear and actionable insights on designing, creating, testing, and procuring secure and privacy-preserving AI systems.
See also this useful recording or the slides from Rob van der Veer’s talk at the OWASP Global appsec event in Dublin on February 15 2023, during which this guide was launched. And check out the Appsec Podcast episode on this guide (audio,video), or the September 2023 MLSecops Podcast. If you want the short story, check out the 13 minute AI security quick-talk.
Please provide your input through pull requests / submitting issues (see repo) or emailing the project lead, and let’s make this guide better and better. Many thanks to Engin Bozdag, lead privacy architect at Uber, for his great contributions.
How to address AI security
This content is now found at the OWASP AI exchange
How to address AI privacy
Privacy principles and requirements come from different legislations (e.g. GDPR, LGPD, PIPEDA, etc.) and privacy standards (e.g. ISO 31700, ISO 29100, ISO 27701, FIPS, NIST Privacy Framework, etc.). This guideline does not guarantee compliance with privacy legislation and it is also not a guide on privacy engineering of systems in general. For that purpose, please consider work from ENISA, NIST, mplsplunk, OWASP and OpenCRE. The general principle for engineers is to regard personal data as ‘radioactive gold’. It’s valuable, but it’s also something to minimize, carefully store, carefully handle, limit its usage, limit sharing, keep track of where it is, etc.
In this section, we will discuss how privacy principles apply to AI systems:
1. Use Limitation and Purpose Specification
Essentially, you should not simply use data collected for one purpose (e.g. safety or security) as a training dataset to train your model for other purposes (e.g. profiling, personalized marketing, etc.) For example, if you collect phone numbers and other identifiers as part of your MFA flow (to improve security ), that doesn’t mean you can also use it for user targeting and other unrelated purposes. Similarly, you may need to collect sensitive data under KYC requirements, but such data should not be used for ML models used for business analytics without proper controls.
Some privacy laws require a lawful basis (or bases if for more than one purpose) for processing personal data (See GDPR’s Art 6 and 9).
In practical terms, you should reduce access to sensitive data and create anonymized copies for incompatible purposes (e.g. analytics). You should also document a purpose/lawful basis before collecting the data and communicate that purpose to the user in an appropriate way.
New techniques that enable use limitation include:
- data enclaves: store pooled personal data in restricted secure environments
- federated learning: decentralize ML by removing the need to pool data into a single location. Instead, the model is trained in multiple iterations at different sites.
Fairness means handling personal data in a way individuals expect and not using it in ways that lead to unjustified adverse effects. The algorithm should not behave in a discriminating way. (See also this article).
GDPR’s Article 5 refers to “fair processing” and EDPS’ guideline defines fairness as the prevention of “unjustifiably detrimental, unlawfully discriminatory, unexpected or misleading” processing of personal data. GDPR does not specify how fairness can be measured, but the EDPS recommends the right to information (transparency), the right to intervene (access, erasure, data portability, rectify), and the right to limit the processing (right not to be subject to automated decision-making and non-discrimination) as measures and safeguard to implement the principle of fairness.
In the literature, there are different fairness metrics that you can use. These range from group fairness, false positive error rate, unawareness, and counterfactual fairness. There is no industry standard yet on which metric to use, but you should assess fairness especially if your algorithm is making significant decisions about the individuals (e.g. banning access to the platform, financial implications, denial of services/opportunities, etc.). There are also efforts to test algorithms using different metrics. For example, NIST’s FRVT project tests different face recognition algorithms on fairness using different metrics.
The elephant in the room for fairness across groups (protected attributes) is that in situations a model is more accurate if it DOES discriminate protected attributes. Certain groups have in practice a lower success rate in areas because of all kinds of societal aspects rooted in culture and history. We want to get rid of that. Some of these aspects can be regarded as institutional discrimination. Others have more practical background, like for example that for language reasons we see that new immigrants statistically tend to be hindered in getting higher education. Therefore, if we want to be completely fair across groups, we need to accept that in many cases this will be balancing accuracy with discrimination. In the case that sufficient accuracy cannot be attained while staying within discrimination boundaries, there is no other option than to abandon the algorithm idea. For fraud detection cases, this could for example mean that transactions need to be selected randomly instead of by using an algorithm.
3. Data Minimization and Storage Limitation
This principle requires that you should minimize the amount, granularity and storage duration of personal information in your training dataset. To make it more concrete:
- Do not collect or copy unnecessary attributes to your dataset if this is irrelevant for your purpose
- Anonymize the data where possible. Please note that this is not as trivial as “removing PII”. See WP 29 Guideline
- If full anonymization is not possible, reduce the granularity of the data in your dataset if you aim to produce aggregate insights (e.g. reduce lat/long to 2 decimal points if city-level precision is enough for your purpose or remove the last octets of an ip address, round timestamps to the hour)
- Use less data where possible (e.g. if 10k records are sufficient for an experiment, do not use 1 million)
- Delete data as soon as possible when it is no longer useful (e.g. data from 7 years ago may not be relevant for your model)
- Remove links in your dataset (e.g. obfuscate user id’s, device identifiers, and other linkable attributes)
- Minimize the number of stakeholders who accesses the data on a “need to know” basis
There are also privacy-preserving techniques being developed that support data minimization:
- distributed data analysis: exchange anonymous aggregated data
- secure multi-party computation: store data distributed-encrypted
Privacy standards such as FIPP or ISO29100 refer to maintaining privacy notices, providing a copy of user’s data upon request, giving notice when major changes in personal data procesing occur, etc.
GDPR also refers to such practices but also has a specific clause related to algorithmic-decision making. GDPR’s Article 22 allows individuals specific rights under specific conditions. This includes getting a human intervention to an algorithmic decision, an ability to contest the decision, and get a meaningful information about the logic involved. For examples of “meaningful information”, see EDPS’s guideline. The US Equal Credit Opportunity Act requires detailed explanations on individual decisions by algorithms that deny credit.
Transparency is not only needed for the end-user. Your models and datasets should be understandable by internal stakeholders as well: model developers, internal audit, privacy engineers, domain experts, and more. This typically requires the following:
- proper model documentation: model type, intent, proposed features, feature importance, potential harm, and bias
- dataset transparency: source, lawful basis, type of data, whether it was cleaned, age. Data cards is a popular approach in the industry to achieve some of these goals. See Google Research’s paper and Meta’s research.
- traceability: which model has made that decision about an individual and when?
- explainability: several methods exist to make black-box models more explainable. These include LIME, SHAP, counterfactual explanations, Deep Taylor Decomposition, etc. See also this overview of machine learning interpretability and this article on the pros and cons of explainable AI.
5. Privacy Rights
Also known as “individual participation” under privacy standards, this principle allows individuals to submit requests to your organization related to their personal data. Most referred rights are:
- right of access/portability: provide a copy of user data, preferably in a machine-readable format. If data is properly anonymized, it may be exempted from this right.
- right of erasure: erase user data unless an exception applies. It is also a good practice to re-train your model without the deleted user’s data.
- right of correction: allow users to correct factually incorrect data. Also, see accuracy below
- right of object: allow users to object to the usage of their data for a specific use (e.g. model training)
6. Data accuracy
You should ensure that your data is correct as the output of an algorithmic decision with incorrect data may lead to severe consequences for the individual. For example, if the user’s phone number is incorrectly added to the system and if such number is associated with fraud, the user might be banned from a service/system in an unjust manner. You should have processes/tools in place to fix such accuracy issues as soon as possible when a proper request is made by the individual.
To satisfy the accuracy principle, you should also have tools and processes in place to ensure that the data is obtained from reliable sources, its validity and correctness claims are validated and data quality and accuracy are periodically assessed.
Consent may be used or required in specific circumstances. In such cases, consent must satisfy the following:
- obtained before collecting, using, updating, or sharing the data
- consent should be recorded and be auditable
- consent should be granular (use consent per purpose, and avoid blanket consent)
- consent should not be bundled with T&S
- consent records should be protected from tampering
- consent method and text should adhere to specific requirements of the jurisdiction in which consent is required (e.g. GDPR requires unambiguous, freely given, written in clear and plain language, explicit and withdrawable)
- Consent withdrawal should be as easy as giving consent
- If consent is withdrawn, then all associated data with the consent should be deleted and the model should be re-trained.
Please note that consent will not be possible in specific circumstances (e.g. you cannot collect consent from a fraudster and an employer cannot collect consent from an employee as there is a power imbalance). If you must collect consent, then ensure that it is properly obtained, recorded and proper actions are taken if it is withdrawn.
8. Model attacks
See the security section for security threats to data confidentiality, as they of course represent a privacy risk if that data is personal data. Notable: membership inference, model inversion, and training data leaking from the engineering process. In addition, models can disclose sensitive data that was unintendedly stored during training.
Scope boundaries of AI privacy
As said, many of the discussion topics on AI are about human rights, social justice, safety and only a part of it has to do with privacy. So as a data protection officer or engineer it’s important not to drag everything into your responsibilities. At the same time, organizations do need to assign those non-privacy AI responsibilities somewhere.
Before you start: Privacy restrictions on what you can do with AI
The GDPR does not restrict the applications of AI explicitly but does provide safeguards that may limit what you can do, in particular regarding Lawfulness and limitations on purposes of collection, processing, and storage - as mentioned above. For more information on lawful grounds, see article 6
In an upcoming update, more will be discussed on the US AI bill of rights.
The US Federal Trade Committe provides some good (global) guidance in communicating carefully about your AI, including not to overpromise.
The EU AI act does pose explicit application limitations, such as mass surveillance, predictive policing, and restrictions on high-risk purposes such as selecting people for jobs. In addition, there are regulations for specific domains that restrict the use of data, putting limits to some AI approaches (e.g. the medical domain).
The EU AI Act in a nutshell:
Human rights are at the core of the AI Act, so risks are analyzed from a perspective of harmfulness to people.
The Act identifies four risk levels for AI systems:
- Unacceptable risk: will be banned. Includes: Manipulation of people, social scoring, and real-time remote biometric identification (e.g. face recognition with cameras in public space).
- High risk: products already under safety legislation, plus eight areas (including critical infrastructure and law enforcement). These systems need to comply with a number of rules including the a security risk assessment and conformity with harmonized (adapted) AI security standards OR the essential requirements of the Cyber Resilience Act (when applicable).
- Limited risk: has limited potential for manipulation. Should comply with minimal transparency requirements to users that would allow users to make informed decisions. After interacting with the applications, the user can then decide whether they want to continue using it.
- Minimal/non risk: the remaining systems.
So organizations will have to know their AI initiatives and perform high-level risk analysis to determine the risk level.
AI is broadly defined here and includes wider statistical approaches and optimization algorithms.
Generative AI needs to disclose what copyrighted sources were used, and prevent illegal content. To illustrate: if OpenAI for example would violate this rule, they could face a 10 billion dollar fine.
Further reading on AI privacy
- NIST AI Risk Management Framework 1.0
- PLOT4ai threat library
- Algorithm audit non-profit organisation
- For pure security aspects: see the ‘Further reading on AI security’ above in this document
This page is the current outcome of the project. The goal is to collect and present the state of the art on these topics through community collaboration. First in the form of this page, and later in other document forms. Please provide your input through pull requests / submitting issues (see repo) or emailing the project lead, and let’s make this guide better and better.
The work in this guide will serve as input to the upcoming ISO/IEC 27090 (AI security) and 27091 (AI privacy) standards, which will be done through membership of ISO/IEC JTC1/SC27/WG4, WG5, CEN/CENELEC JTC 21/WG1-TG, and the SC42 AHG4 group.
Put whatever you like here: news, screenshots, features, supporters, or remove this file and don’t use tabs at all.