Neural Information Processing Systems http://nips.cc/

Thank you for your insightful comments. These results clearly illustrate the importance of training a powerful core network. This shows that our method is more effective with limited training data. We will include an in-depth study. Thank you, we will clarify this.

This paper makes the observation that existing models are ill-suited for PI and proposes a novel NAS method, named CryptoNAS, for finding and tailoring models to the needs of PI.

The authors present an interesting paper about a backpropagation training method using spike probabilities and takes into account the hardware constraints of a particular platform which has spiking neurons and discrete synapses. This is a topic of current interest in mapping deep networks to multi-neuron hardware platforms. Quality: The proposed training method is useful especially in consideration of new multi-neuron hardware platforms with constraints. Clarity: The paper is easy to read. The claims made at the end of Section 1 can be reworded because as it stands, if not read carefully, suggests that the paper proposes for the first time a training methodology that employs spiking neurons, synapses with reduced precision.

The integration of Machine Learning and Artificial Intelligence (ML/AI) into fifth-generation (5G) networks has made evident the limitations of network intelligence with ever-increasing, strenuous requirements for current and next-generation devices. This transition to ubiquitous intelligence demands high connectivity, synchronicity, and end-to-end communication between users and network operators, and will pave the way towards full network automation without human intervention. Intent-based networking is a key factor in the reduction of human actions, roles, and responsibilities while shifting towards novel extraction and interpretation of automated network management. This paper presents the development of a custom Large Language Model (LLM) for 5G and next-generation intent-based networking and provides insights into future LLM developments and integrations to realize end-to-end intent-based networking for fully automated network intelligence.

Large language models (LLMs) are rapidly emerging in Artificial Intelligence (AI) applications, especially in the fields of natural language processing and generative AI. Not limited to text generation applications, these models inherently possess the opportunity to leverage prompt engineering, where the inputs of such models can be appropriately structured to articulate a model's purpose explicitly. A prominent example of this is intent-based networking, an emerging approach for automating and maintaining network operations and management. This paper presents semantic routing to achieve enhanced performance in LLM-assisted intent-based management and orchestration of 5G core networks. This work establishes an end-to-end intent extraction framework and presents a diverse dataset of sample user intents accompanied by a thorough analysis of the effects of encoders and quantization on overall system performance. The results show that using a semantic router improves the accuracy and efficiency of the LLM deployment compared to stand-alone LLMs with prompting architectures.

The $5^{th}$ generation of mobile networks introduces a new Network Function (NF) that was not present in previous generations, namely the Network Data Analytics Function (NWDAF). Its primary objective is to provide advanced analytics services to various entities within the network and also towards external application services in the 5G ecosystem. One of the key use cases of NWDAF is mobility trajectory prediction, which aims to accurately support efficient mobility management of User Equipment (UE) in the network by allocating ``just in time'' necessary network resources. In this paper, we show that there are potential mobility attacks that can compromise the accuracy of these predictions. In a semi-realistic scenario with 10,000 subscribers, we demonstrate that an adversary equipped with the ability to hijack cellular mobile devices and clone them can significantly reduce the prediction accuracy from 75\% to 40\% using just 100 adversarial UEs. While a defense mechanism largely depends on the attack and the mobility types in a particular area, we prove that a basic KMeans clustering is effective in distinguishing legitimate and adversarial UEs.

In this paper we introduce a first attempt on understanding how a non-autoregressive factorised multi-speaker speech synthesis architecture exploits the information present in different speaker embedding sets. We analyse if jointly learning the representations, and initialising them from pretrained models determine any quality improvements for target speaker identities. In a separate analysis, we investigate how the different sets of embeddings impact the network's core speech abstraction (i.e. zero conditioned) in terms of speaker identity and representation learning. We show that, regardless of the used set of embeddings and learning strategy, the network can handle various speaker identities equally well, with barely noticeable variations in speech output quality, and that speaker leakage within the core structure of the synthesis system is inevitable in the standard training procedures adopted thus far.