Improving Mobile Interactive Video QoE via Two-Level Online Cooperative Learning

Zhang, Huanhuan; Zhou, Anfu; Ma, Huadóng

doi:10.1109/tmc.2022.3179782

Cited by 9 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We discuss the diversity of real-world network traffic distributions in §. In line with state-of-art work (Huang et al 2023;Zhang, Zhou, and Ma 2022), we also consider the deep reinforcement learning methods for local training. Each client trains a local policy π i by maximizing its accumulated reward…”

Section: Learning Abrs In Fl-based Frameworkmentioning

confidence: 99%

Adversarial Attacks on Federated-Learned Adaptive Bitrate Algorithms

Zhang,

Huang

2024

AAAI

View full text Add to dashboard Cite

Learning-based adaptive bitrate (ABR) algorithms have revolutionized video streaming solutions. With the growing demand for data privacy and the rapid development of mobile devices, federated learning (FL) has emerged as a popular training method for neural ABR algorithms in both academia and industry. However, we have discovered that FL-based ABR models are vulnerable to model-poisoning attacks as local updates remain unseen during global aggregation. In response, we propose MAFL (Malicious ABR model based on Federated Learning) to prove that backdooring the learning-based ABR model via FL is practical. Instead of attacking the global policy, MAFL only targets a single ``target client''. Moreover, the unique challenges brought by deep reinforcement learning (DRL) make the attack even more challenging. To address these challenges, MAFL is designed with a two-stage attacking mechanism. Using two representative attack cases with real-world traces, we show that MAFL significantly degrades the model performance on the target client (i.e., increasing rebuffering penalty by 2x and 5x) with a minimal negative impact on benign clients.

show abstract

Section: Learning Abrs In Fl-based Frameworkmentioning

confidence: 99%

Adversarial Attacks on Federated-Learned Adaptive Bitrate Algorithms

Zhang,

Huang

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…We first design a dynamic network condition discriminator to identify each user's network type and transportation mode. Especially, the network type (e.g., 3G, 4G, and WiFi) can be directly obtained from internet service providers (ISP) [9], and the transportation mode (e.g., car, bus, ferry, and train) can be detected using mobile sensors (e.g., GPS, accelerometers or microphones) [7]. Users are classified into 12 groups (labeled as 𝐺, which can be extended to the more general group classification) as depicted in Table 1.…”

Section: Bamboo Designmentioning

confidence: 99%

“…Existing works primarily involve offline and online learning methods. Most of them are limited to the offline mode, applying the "learning offline, running online" strategy [8], which inevitably suffers from the simulation-to-reality gap. Compared with offline learning, online learning supports the training along with video streaming service, continuously refining RL models in response to new environments instead of relying on pre-trained models.…”

Section: Introductionmentioning

confidence: 99%

Bamboo: Boosting Training Efficiency for Real-Time Video Streaming via Online Grouped Federated Transfer Learning

Zheng,

Chen,

2023

Proceedings of the 7th Asia-Pacific Workshop on Networking

View full text Add to dashboard Cite

“…TCP and VoD optimization. As a persistent problem along with the Internet's evolution, (i) TCP evolves from traditionally newReno [78], Cubic [48] to BBR [30] and PCC [79], and has also tailed for cellular networks [20], [80], [81], [82], or for better delivering real-time video [83], [84], [85]. (ii) Video streaming ABR algorithms are traditionally designed based on instantaneous throughput and buffer-level [67], [86], or further enhanced by physical layer information [22].…”

Section: F Impact Of Implementation Approximationmentioning

confidence: 99%

Octopus: Exploiting the Edge Intelligence for Accessible 5G Mobile Performance Enhancement

Zhou

Pei

et al. 2023

IEEE/ACM Trans. Networking

View full text Add to dashboard Cite

While 5G has rolled out since 2019 and exhibited versatile advantages, its performance under high/extreme mobility scenes (e.g., driving, high-speed railway or HSR) remains mysterious. In this work, we carry out a large-scale field-trial campaign, taking >13,000 Km round-trips on HSR moving at 250-350 Km/h, with operational 5G cellular coverage along the railway. Our empirical study reveals that coupling interaction among high mobility, 5G handover characteristics, and applications' sluggish reaction to handover, results in catastrophic damage to user experience: low TCP bandwidth utilization of 26.6% and glitchy 4K VoD streaming. To solve the problem, we propose an edge-assisted mobility management framework called Octopus. Different from previous works, Octopus aims at a standard-compatible and easy-to-deploy solution, thus we take a new design paradigm of exploiting the edge intelligence on multi-access edge computing (MEC). We realize Octopus as a universal MEC service ready for benefiting any third-party mobile applications. We prototype, deploy, and evaluate Octopus in operational 5G, which demonstrates the significant performance gain across the full-range mobile scenarios, e.g., HSR, driving, and walking.

show abstract

Improving Mobile Interactive Video QoE via Two-Level Online Cooperative Learning

Cited by 9 publications

References 30 publications

Adversarial Attacks on Federated-Learned Adaptive Bitrate Algorithms

Adversarial Attacks on Federated-Learned Adaptive Bitrate Algorithms

Bamboo: Boosting Training Efficiency for Real-Time Video Streaming via Online Grouped Federated Transfer Learning

Octopus: Exploiting the Edge Intelligence for Accessible 5G Mobile Performance Enhancement

Contact Info

Product

Resources

About