Short-form video streaming is characterized by fast-paced, scrolling-driven user interactions. This poses unique challenges for its streaming algorithm design. To our knowledge, there is little understanding of how short video streaming algorithms perform in large-scale production platforms. To bridge this gap, this paper reports our two-year experience in evolving the prefetching algorithm, a critical algorithmic component for short video streaming, deployed in a leading global short video service. We adopt an iterative, production-driven approach, progressively evolving the design from simple heuristics to optimization-based and data-driven algorithms, with each iteration validated through large-scale A/B tests on hundreds of millions of users. Our evolution advances two core components: the prefetching logic and the viewing time estimation, including a lightweight on-device personalization mechanism. Through carefully balancing startup delay, mid-playback stalls, bandwidth usage, runtime overhead, and estimation accuracy, we achieve a 0.38% increase in user stay time - our key engagement metric - while simultaneously reducing bandwidth consumption by 14.7% throughout the evolution. We distill actionable insights from real-world deployment, highlighting the importance of startup latency, bandwidth efficiency, and low-overhead design for short video streaming at scale.

Intrusion detection systems (IDS) are crucial tools for detecting anomalous network traffic in cybersecurity. In recent years, significant progress has been made in applying artificial intelligence to IDS. However, existing research often assumes that training and testing data are static and identically distributed, whereas in reality, data drift is inevitable. Moreover, to enhance model versatility and detection performance, models have become increasingly complex, posing challenges to real-time deployment. To address these challenges, we propose an adaptive network intrusion detection system named A-NIDS, consisting of a main task and two bypass tasks. The main task is to develop a fully connected and shallow network with strong detection performance and real-time capability. The first bypass task is a clustering model that helps the main task detect data drift in an unsupervised manner. The second bypass task is a generation model to generate old data to address catastrophic forgetting in new model iterations and the storage cost issue caused by accumulating old data. We conduct extensive experiments on the CICIDS-2017 and CSE-CICIDS-2018 datasets, demonstrating the superior performance of A-NIDS on new and old data. Furthermore, our detection module achieves a detection latency of 5 microseconds, highlighting its suitability for real-time applications. All the related code is publicly available at:https://github.com/ids-sec-hub/A-NIDS.

The machine learning-based approach to network intrusion detection presents a groundbreaking research paradigm, positioned to replace traditional rule-based and signature-based methods. However, prior research methodologies have predominantly focused on flow-based approaches, which may not be effective in detecting all types of attacks at a granular level. In this study, we introduce DM-IDS, an attention-convolution architecture model for bimodal network intrusion detection in both flow and payload modalities, using bilinear fusion. Notably, we present a novel method for constructing binary-form feature vectors under the payload modality, with the goal of extracting additional security semantic features. To facilitate this, we independently develop a feature generation tool named Beeman. Finally, we conduct a series of comparative and ablation experiments on two publicly available datasets, CICIDS-2017 and CICIoT-2023, achieving state-of-the-art model performance.

Deep neural networks have been successfully applied in many computer vision tasks. However, these models suffer catastrophic forgetting when learning new knowledge incrementally. To overcome the stability-plasticity dilemma, class incremental learning (CIL) has been widely discussed recently. The state-of-the-art CIL methods mainly leverage additional exemplar sets, thus memory costly and may raise privacy issues. To that end, we propose an autonomous generative feature replay (AGFR) framework without using exemplar sets. It consists of three modules: the feature extractor module, the feature generator module, and the unified classification module. First, to stabilize features over tasks, robust feature extractors are learned in a self-supervised manner and thus generalize well to unseen data. Second, instead of using exemplar sets or producing raw images, we propose an autonomous generative feature replay scheme to constantly update unified classifier in CIL without saving any image data. This strategy avoids overwhelming memory usage or poor quality of the generated raw images. Experiments demonstrate that our method achieves state-of-the-art performance in terms of average classification accuracy.⋆

Traditional shape descriptors have been gradually replaced by convolutional neural networks due to their superior performance in feature extraction and classification. The state-of-the-art methods recognize object shapes via image reconstruction or pixel classification. However, these methods are biased toward texture information and overlook the essential shape descriptions, thus, they fail to generalize to unseen shapes. We are the first to propose a few-shot shape descriptor (FSSD) to recognize object shapes given only one or a few samples. We employ an embedding module for FSSD to extract transformation-invariant shape features. Secondly, we develop a dual attention mechanism to decompose and reconstruct the shape features via learnable shape primitives. In this way, any shape can be formed through a finite set basis, and the learned representation model is highly interpretable and extendable to unseen shapes. Thirdly, we propose a decoding module to include the supervision of shape masks and edges and align the original and reconstructed shape features, enforcing the learned features to be more shape-aware. Lastly, all the proposed modules are assembled into a few-shot shape recognition scheme. Experiments on five datasets show that our FSSD significantly improves the shape classification compared to the state-of-the-art under the few-shot setting.

The emergence of 360-video streaming systems has brought about new possibilities for immersive video experiences while requiring significantly higher bandwidth than traditional 2D video streaming. Viewport prediction is used to address this problem, but interesting storylines outside the viewport are ignored. To address this limitation, we present SAVG360, a novel viewport guidance system that utilizes global content information available on the server side to enhance streaming with the best saliency-captured storyline of 360-videos. The saliency analysis is performed offline on the media server with powerful GPU, and the saliency-aware guidance information is encoded and shared with clients through the Saliency-aware Guidance Descriptor. This enables the system to proactively guide users to switch between storylines of the video and allow users to follow or break guided storylines through a novel user interface. Additionally, we present a viewing mode prediction algorithms to enhance video delivery in SAVG360. Evaluation of user viewport traces in 360-videos demonstrate that SAVG360 outperforms existing tiled streaming solutions in terms of overall viewport prediction accuracy and the ability to stream high-quality 360 videos under bandwidth constraints. Furthermore, a user study highlights the advantages of our proactive guidance approach over predicting and streaming of where users look.

360-degree video has become increasingly popular in content consumption. However, finding the viewing direction for important content within each frame poses a significant challenge. Existing approaches rely on either viewer input or algorithmic determination to select the viewing direction, but neither mode consistently outperforms the other in terms of content-importance. In this paper, we propose 360TripleView, the first view management system for 360-degree video that automatically infers and utilizes the better view mode for each frame, ultimately providing viewers with higher content-importance views. Through extensive experiments and a user study, we demonstrate that 360TripleView achieves over 90% accuracy in inferring the better mode and significantly enhances content-importance compared to existing methods.

Given high-speed mobile Internet access today, audiences are expecting much higher video quality than before. Video service providers have deployed dynamic video bitrate adaptation services to fulfill such user demands. However, legacy video bitrate adaptation techniques are highly dependent on the estimation of dynamic bandwidth, and fail to integrate the video quality enhancement techniques, or consider the heterogeneous computing capabilities of client devices, leading to low quality of experience (QoE) for users. In this paper, we present a super-resolution based adaptive video streaming (SRAVS) framework, which applies a Reinforcement Learning (RL) model for integrating the video super-resolution (VSR) technique with the video streaming strategy. The VSR technique allows clients to download low bitrate video segments, reconstruct and enhance them to high-quality video segments while making the system less dependent on estimating dynamic bandwidth. The RL model investigates both the playback statistics and the distinguishing features related to the client-side computing capabilities. Trace-driven emulations over real-world videos and bandwidth traces verify that SRAVS can significantly improve the QoE for users compared to the state-of-the-art video streaming strategies with or without involving VSR techniques.