Internet-Draft AI/ML security privacy implications April 2024
Sarikaya & Schott Expires 4 October 2024 [Page]
Network Working Group
Intended Status:
Standards Track
B. Sarikaya
R. Schott
Deutsche Telekom

Security and Privacy Implications of 3GPP AI/ML Networking Studies for 6G


This document provides an overview of 3GPP work on Artificial Intelligence/ Machine Learning (AI/ML) networking. Application areas and corresponding proposed modifications to the architecture are identified. Security and privacy issues of these new applications need to be identified out of which IETF work could emerge.

Status of This Memo

This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.

Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at

Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."

This Internet-Draft will expire on 4 October 2024.

Table of Contents

1. Introduction

Artificial Intelligence (AI) has historically been defined as the science and engineering to build intelligent machines capable of carrying out tasks as humans do. Inspired from the way human brain works, machine learning (ML) is defined as the field of study that gives computers the ability to learn without being explicitly programmed. Since it is believed that the main computational elements in a human brain are 86 billion neurons, the more popular ML approaches are using “neural network” as the model. Neural networks (NN) take their inspiration from the notion that a neuron’s computation involves a weighted sum of the input values. A computational neural network contains the neurons in the input layer which receive some values and propagate them to the neurons in the middle layer of the network, which is also called a “hidden layer”. The weighted sums from one or more hidden layers are ultimately propagated to the output layer, which presents the final outputs of the network.

Neural networks having more than three layers, i.e., more than one hidden layer are called deep neural networks (DNN). In contrast to the conventional shallow-structured NN architectures, DNNs, also referred to as deep learning, made amazing breakthroughs since 2010s in many essential application areas because they can achieve human-level accuracy or even exceed human accuracy. Deep learning techniques use supervised and/or unsupervised strategies to automatically learn hierarchical representations in deep architectures for classification. With a large number of hidden layers, the superior performance of DNNs comes from its ability to extract high-level features from raw sensory data after using statistical learning over a large amount of data to obtain an effective representation of an input space. In recent years, thanks to the big data obtained from the real world, the rapidly increased computation capacity and continuously-evolved algorithms, DNNs have become the most popular ML models for many AI applications.

The performance of DNNs is gained at the cost of high computational complexity. Hence more efficient compute engines are often used, e.g. graphics processing units (GPU) and network processing units (NPU). Compared to the inference which only involves the feedforward process, the training often requires more computation and storage resources because it involves also the back propagation process.

Many DNN models have been developed over the past two decades. Each of these models has a different “network architecture” in terms of number of layers, layer types, layer shapes (i.e., filter size, number of channels and filters), and connections between layers. Three popular structures of DNNs: multilayer perceptron (MLPs), convolution neural networks (CNNs), and recurrent neural networks (RNNs). Multilayer perceptron (MLP) model is the most basic DNN, which is composed of a series of fully connected layers. In a fully connected layer, all outputs are connected to all inputs. Hence MLP requires a significant amount of storage and computation.

A convolution neural network (CNN) is composed of multiple convolutional layers. Applying various convolutional filters, CNN models can capture the high-level representation of the input data, making it popular for image classification and speech recognition tasks. Recurrent neural network (RNN) models are another type of DNNs, which use sequential data feeding. The input of RNN consists of the current input and the previous samples. RNN models have been widely used in the natural language processing task on mobile devices, e.g., language modeling, machine translation, question answering, word embedding, and document classification.

AI/ML has very many applications, however, two areas have emerged that involve networking. One is the network optimization, time-series forecasting, predictive maintenance, Quality of Experience (QoE) modeling and the other is speech recognition, image recognition, video processing. In the former, the end device is the base station and the latter the UE [TR22.874].

This document aims to present Artificial Intelligence Machine Learning (AIML) networking issues that may require further protocol work, mostly on the security and privacy aspects of networking.

2. Training and Federated Learning

Training is a process in which an AI/ML model learns to perform its given tasks, more specifically, by optimizing the value of the weights in the DNN. A DNN is trained by inputting a training set, which are often correctly-labelled training samples. Taking image classification for instance, the training set includes correctly-classified images. The training process is repeated iteratively to continuously reduce the overall loss. Until the loss is below a predefined threshold, the DNN with high precision is obtained. After a DNN is trained, it can perform its task by computing the output of the network using the weights determined during the training process, which is referred to as inference. In the model inference process, the inputs from the real world are passed through the DNN. Then the prediction for the task is output. For instance, the inputs can be pixels of an image, sampled amplitudes of an audio wave or the numerical representation of the state of some system or game. Correspondingly, the outputs of the network can be a probability that an image contains a particular object.

With continuously improving capability of cameras and sensors on mobile devices, valuable training data, which are essential for AI/ML model training, are increasingly generated on the devices. For many AI/ML tasks, the fragmented data collected by mobile devices are essential for training a global model. In the traditional approaches, the training data gathered by mobile devices are centralized to the cloud datacenter for a centralized training.

In Distributed Learning mode, each computing node trains its own DNN model locally with local data, which preserves private information locally. To obtain the global DNN model by sharing local training improvement, nodes in the network will communicate with each other to exchange the local model updates. In this mode, the global DNN model can be trained without the intervention of the cloud datacenter.

In 3GPP Federated Learning (FL) mode, the cloud server trains a global model by aggregating local models partially-trained by each end devices. The most agreeable Federated Learning algorithm so far is based on the iterative model averaging whereby within each training iteration, a UE performs the training based on the model downloaded from the AI server using the local training data. Then the UE reports the interim training results (e.g., gradients for the DNN) to the cloud server via 5G uplink (UL) channels. The server aggregates the gradients from the UEs, and updates the global model. Next, the updated global model is distributed to the UEs via 5G Data Link (DL) channels. Then the UEs can perform the training for the next iteration.

Summarizing, we can say that distributed learning is about having centralized data but distributing the model training to different nodes, while federated learning (FL) is about having decentralized data and training and in effect having a central model [Srini21]

3. Architecture

A new framework for protocols called Service based architecture (SBA) comprises Network Functions (NFs) that expose services through RESTful APIs has been defined. There are providers and consumers (publishers and subscribers) which are new functions in the system [IsNo20].

3GPP core, i.e., 5GC network, aka mobile core network, which establishes reliable, secure connectivity to the network for end users and provides access to its services has a new server function: The Network Data Analytics Function (NWDAF) provides analytics to Mobile Core Network Functions (NFs) and Operations and Management (OAM). An NWDAF may contain the Analytics logical function (AnLF): A logical function in NWDAF, which performs inference, derives analytics information and Model Training logical function (MTLF) which trains Machine Learning (ML) models and exposes new training services. The Application AI/ML operation logic is controlled by an Application Function (AF). Any AF request to the 5G System in the context of 5G System (5GS) (which consists of the 5GC (5G Core Network), 5G-AN (5G Access Network) and UE) assistance to Application AI/ML operation should be authorized by the Mobile Core Network [TR23.700-80].

NWDAF relies on various sources of data input including data from 5G core NFs, AFs, 5G core repositories, e.g., Network Repository Function (NRF), Unified Data Management (UDM), etc., and OAM data, including performance measurements (PMs), Key Performance Indicators (KPIs), configuration management data and alarms. An NWDAF may provide in turn analytics output results to 5G core NF, AFs, and OAM. Optionally, Data Collection Coordination Function (DCCF) and Messaging Framework Adaptor Function (MFAF) may be involved to distribute and collect repeated data towards or from various data sources. Note that AF contains a Network Exposure Function (NEF) if it is an untrusted AF. NEF may assist the AI/ML application server in scheduling available UE(s) to participate in the AI/ML operation, e.g., Federated Learning. Also, Mobile Core Network may assist the selection of UEs to serve as FL clients, by providing a list of target member UE(s), then subscribing to the NEF to be notified about the subset list of UE(s) (i.e., list of candidate UE(s)) that fulfill certain filtering criteria [TR23.700-82].

3.1. AI/ML for Vertical Markets

Vertical markets cover automotive such as cars, drones and IoT based smart factories are the major consumers of 3GPP-provided data analytics services. They play important role on the Exposure of data analytics services from different network domains to the verticals in a unified manner. Essentially they define, at an overarching layer, value-add application data analytics services which cover stats/predictions for the end-to-end application service.

Example use case is the Vertical user leveraging the Application layer Analytics capabilities for predicting end to end performance and selecting the optimal vertical application layer (VAL) server [TS23.436].

[TR23.700-82] expands upon the data analytics as a useful tool to optimize the service offering by predicting events related to the network or UE conditions. These services however can also assist the 3rd party AI/ML application service provider for the AI/ML model distribution, transfer, training for various applications (e.g., video/speech recognition, robot control, automotive). This takes us to the concept of the application enablement layer can play role on the exposure of AI/ML services from different 3GPP domains to the Application Service Providers (ASP) in a unified manner.

4. Security and Privacy

AI/ML networking raises many security and privacy issues. [TR23.700-80] and [TR23.700-82] identify a number of key issues and [TR33.898] presents a study on one of the key issues which will be detailed here.

[TR23.700-80] studies the exposure of different types of assistance information such as traffic rate, packet delay, packet loss rate, network condition changes, candidate FL members, geographical distribution information, etc., to AF for AI / ML operations. Some of assistance information could be user privacy sensitive, such as candidate FL members, geographical distribution information. There is a need to study how to protect such privacy-related assistance information. In addition, Mobile Core Network needs to determine which assistance information is required by AF to complete AI/ML operation and to avoid exposing information that is unnecessary for AI/ML operations.

Because of the use of Restful API which depend on the use of HTTP protocol, OAuth [RFC6749] protocol seems to be the natural choice here for authorization.

One solution can be developed reusing existing mechanism for authorization of Mobile Core Network assistance information exposure to AF. The solution is based on reusing the OAuth-based authorization mechanism OAuth [RFC6749] protocol which extends traditional client-server authentication by providing a third-party client with a token. Since such token resembles a different set of credentials compared to those of the resource owner, the device needs not be allowed to use the resource owner's credentials to access protected resources.

UE privacy profile/local policies stored in a database can also be employed to authorize UE-related Mobile Core Network assistance information exposure. UE privacy profile/local policies may also contain protection policies that indicate how Mobile Core Network assistance information should be protected (e.g., encryption, integrity protection, etc.). NWDAF via Network Exposure Function (NEF) sends the UE-related Mobile Core Network assistance information to AF when the local policies/UE privacy profile authorize the AF to access the information. According to the local policies/UE privacy profiles, NWDAF may need to protect the Mobile Core Network assistance information with security mechanisms.

Network Functions securely expose capabilities and events to 3rd party Application Functions (AF) via Network Exposure Function (NEF). The interface between the NEF and the Application Function needs integrity protection, replay protection, confidentiality protection for communication between the NEF and Application Function, and mutual authentication between the NEF and Application Function and protect internal 5G Core network information. The NEF also enable secure provision of information in the 3GPP network by authenticated and authorized AFs.

Security should be provided to support the protection of user privacy sensitive assistance information being exposed to AF. TLS 1.3 [RFC8446] is used to provide integrity protection, replay protection and confidentiality protection for the interface between the NEF and the AF [TS33.501].

5. Work Points

Security and privacy of AI/ML Networking based services and applications need further work. [TR33.898] provides solutions to only one of many possible key issues. Each key issue has been in depth investigated in [TR23.700-80] and [TR23.700-82] from which new solutions can be developed.

We list below only some of the key issues identified:

5.1. Future Work

A use case document is needed. So far 3GPP identified many use cases and some of which are described above in this document. New set of use cases on Rule Based Automation, Autonomous Networks, Automated Testing, Energy Efficiency and so on could be added to the existing use cases. All or some of these usage areas of AI/ML can further be elaborated in a use case document These use cases should make it clear why the security and privacy protocols are needed.

A problem statement on AI/ML networking document is needed. Such a document should identify the problems that possibly need a new protocol to be developed or need to identify extensions to an existing protocol. One possibility in that direction could be refining the work points identified above and formulating them in terms of existing or to be defined in the future security and privacy protocols.

6. Security Considerations

Security considerations of AI/ML Networking is TBD.

7. IANA Considerations

There are no IANA considerations for this document.

8. Acknowledgements

We acknowledge useful comments from Hesham ElBakoury.

9. References

9.1. Normative References

Hardt, D., Ed., "The OAuth 2.0 Authorization Framework", RFC 6749, DOI 10.17487/RFC6749, , <>.
Rescorla, E., "The Transport Layer Security (TLS) Protocol Version 1.3", RFC 8446, DOI 10.17487/RFC8446, , <>.

9.2. Informative References

Isaksson, M. and C. Norrman, "Secure Federated Learning in 5G Mobile Networks", , <>.
Srinivasan, A., "Difference between distributed learning versus federated learning algorithms", , <>.
3rd Generation Partnership Project, "Study on traffic characteristics and performance requirements for AI/ML model transfer in 5GS", .
3rd Generation Partnership Project, "Study on 5G System Support for AI/ML-based Services", .
3rd Generation Partnership Project, "Study on application layer support for AI/ML services", .
3rd Generation Partnership Project, "Study on security and privacy of Artificial Intelligence/Machine Learning (AI/ML)-based services and applications in 5G", .
3rd Generation Partnership Project, "Functional architecture and information flows for Application Data Analytics Enablement Service", , <>.
3rd Generation Partnership Project, "Security Architecture and Procedures for 5G System", , <>.

Authors' Addresses

Behcet Sarikaya
Roland Schott
Deutsche Telekom
Ida-Rhodes-Strasse 2
64295 Darmstadt