This book constitutes the refereed proceedings of the Second International Conference on Artificial Intelligence Security and Privacy, AIS&P 2024, held in Guangzhou, China, during December 6-7, 2024.The 14 full papers included in this book were carefully reviewed and selected from 47 submissions.

.- BadHAR: Backdoor Attacks in Federated Human Activity Recognition Systems. .- Fully Automated Generation Mechanism of Rootfs for Specified Operating Systems under Linux. .- Anti-Side-Channel Attack Mechanisms in Blockchain Payment Channels. .- F2L: A Lightweight Focus Layer against Backdoor Attack in Federated Learning. .- Intelligent backpack based on ireless mobile technology. .- Tourism Industry Upgrading and Public Opinion Prevention Methods Based on BERTopic: A Case Study of Hotel Management. .- Privacy-Preserving Covert Channels in VoLTE via Inter-Frame Delay Modulation. .- Enhancing Adversarial Robustness in Object Detection via Multi-Task Learning and Class-Aware Adversarial Training. .- FedHKD: A Hierarchical Federated Learning Approach Integrating  lustering and Knowledge Distillation for Non-IID Data. .- Application of Ensemble Learning Based on High-Dimensional Features in Financial Big Data. .- Collaborative Framework for Dynamic Knowledge Updating and Transparent Reasoning with Large Language Models. .- Zero-Shot Dense Retrieval based on Query Expansion. .- Lightweight Attention-CycleGAN for Nighttime-Daytime Image ransformation. .- Generative Image Steganography Based on Latent Space Vector Coding and Diffusion Model.