RTFL: Energy-Aware Federated Learning for AIoT Design Via Adaptive Quantization-based Multi-Agent Scheduling (EDA Top Conference, CCF-A, Acceptance Ratio: 25%)

Jun Xia, Junqi Zhang, Zhaorong Zhu, Wenjie Chen, Mingsong Chen.

Project

• We introduce RTFL, a novel energy-aware Real-Time Federated Learning framework based on Multi-Agent Reinforcement Learning (MARL), aiming to enhance the knowledge sharing across AIoT devices within a specified training time constraint. Specifically, RTFL employs an Adaptive Quantization-based Multi-Agent Scheduling (AQMAS) strategy, enabling a team of agents to intelligently select devices with specific model quantization levels for each round of local training, taking into account the resource constraints (e.g., remaining battery power, computing capability, and communication bandwidth) of the current devices.

WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks (Machine Learning Top Conference, CCF-A, Acceptance Ratio: 25%)

Jun Xia, Zhihao Yue, Yingbo Zhou, Zhiwei Ling, Yiyu Shi, Xian Wei, Mingsong Chen

Project

• We obtain image high-frequency features through the Discrete Wavelet Transform (DWT) to generate backdoor triggers.

Towards Energy-Aware Federated Learning via MARL: A Dual-Selection Approach for Model and Client (EDA Top Conference, CCF-B, Acceptance Ratio: 24%)

Jun Xia, Yi Zhang, Yiyu Shi

Project

• We propose an energy-aware FL framework named DR-FL, which considers the energy constraints in both clients and heterogeneous deep learning models to enable energy-efficient FL. Unlike Vanilla FL, DR-FL adopts our proposed Multi-Agent Reinforcement Learning (MARL)-based dual-selection method, which enables participating devices to make effective and adaptive contributions to the global model based on their computing capabilities and energy capacities in a MARL-based manner.

Eliminating backdoor triggers for deep neural networks using attention relation graph distillation (AI Top Conference, CCF-A, Acceptance Ratio: 14%)

Jun Xia, Ting Wang, Jiepin Ding, Xian Wei, Mingsong Chen

Project

• We introduce a novel backdoor defense framework named Attention Relation Graph Distillation (ARGD), which fully explores the correlation among attention features with different orders using our proposed Attention Relation Graphs (ARGs). Based on the alignment of ARGs between both teacher and student models during knowledge distillation, ARGD can eradicate more backdoor triggers than NAD.

Accelerated synthesis of neural network-based barrier certificates using collaborative learning (EDA Top Conference, CCF-A, Acceptance Ratio: 23%)

Jun Xia, Ming Hu, Xin Chen, Mingsong Chen

Project

• We fully exploit the parallel processing capability of the underlying hardware to enable a quick search for a barrier certificate.

PervasiveFL: Pervasive federated learning for heterogeneous IoT systems (EDA Top Journal, CCF-A, Acceptance Ratio: 23%)

Jun Xia, Tian Liu, Zhiwei Ling, Ting Wang, Xin Fu, Mingsong Chen

Project

• We propose a novel framework named PervasiveFL that enables efficient and effective FL among heterogeneous IoT devices. Without modifying original local models, PervasiveFL installs one lightweight NN model named modellet on each device. By using the deep mutual learning (DML) and our entropy-based decision gating (EDG) method, modellets and local models can selectively learn from each other through soft labels.

Fast3DGSW: Toward Fast and Robust Watermarking for Quantization-Aware 3D Gaussian Splatting (Computer Vision Top Conference, CCF-A, Acceptance Ratio: 25%)

Boyu Wang, Jun Xia, Mingsong Chen

Project

Model-Contrastive Learning for Backdoor Elimination (Multi-Media Top Conference, CCF-A, Acceptance Ratio: 25%)

Zhihao Yue, Jun Xia, Zhiwei Ling, Ming Hu, Ting Wang, Xian Wei, Mingsong Chen

Project

• In this paper, we propose a novel two-stage backdoor defense method, named MCLDef, based on Model-Contrastive Learning (MCL). MCLDef can purify the backdoored model by pulling the feature representations of poisoned data towards those of their clean data counterparts.

Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis(EDA Top Conference, CCF-A iter, Acceptance Ratio: 25%)

Ruiyang Qin, Jun Xia, Zhenge Jia, Meng Jiang, Ahmed Abbasi, Peipei Zhou, Jingtong Hu, Yiyu Shi

Project

• In this paper, we propose a novel framework to select and store the most representative data online in a self-supervised way. Such data has a small memory footprint and allows infrequent requests of user annotations for further fine-tuning.

Model-Contrastive Learning for Backdoor Elimination (Multi-Media Top Conference, CCF-A, Acceptance Ratio: 25%)

Zhihao Yue, Jun Xia, Zhiwei Ling, Ming Hu, Ting Wang, Xian Wei, Mingsong Chen

Project

• In this paper, we propose a novel two-stage backdoor defense method, named MCLDef, based on Model-Contrastive Learning (MCL). MCLDef can purify the backdoored model by pulling the feature representations of poisoned data towards those of their clean data counterparts.