arXiv subjects

Zhujun Xiao

Publications and source records attributed to Zhujun Xiao.

6 recordsLinked to original sources

arXiv2026

From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation

Industry-scale video and live-streaming moderation imposes requirements that are difficult to satisfy with generic pretrained public models or external APIs, including adaptation to platform-specific data distributions, policy-specific objectives, and product-level safety constraints. As a result, platforms must undertake internal model development, naturally turning to shared public research for guidance. However, existing multimodal foundation-model studies primarily report architectures, training recipes, data scaling strategies, and benchmark results, but provide less systematic guidance on how failures should be localized and translated into targeted model-development interventions. Interventions are essential because deployment failures are rarely self-explanatory. Similar failures can originate from different causes. Without targeted interventions, improvement reduces to heuristic trial-and-error, where benchmark improvements are weakly attributable, and failures are difficult to trace to their underlying causes. To address this gap, we present a diagnostic methodology for industry-scale Audio-Visual-Language Models AVLM development. The methodology maps model failures into a taxonomy of observable failure signatures and links each class of failure to an intervention space. We instantiate this methodology across the development and alignment lifecycle of an AVLM foundation model for a large-scale video and live-streaming platform. The resulting system supports over 100 regions and is designed for noisy, ambiguous, and highly diverse content drawn from global platform traffic.

cs.LG↗

arXiv2021

On The Robustness of Price-Anticipating Kelly Mechanism

The price-anticipating Kelly mechanism (PAKM) is one of the most extensively used strategies to allocate divisible resources for strategic users in communication networks and computing systems. The users are deemed as selfish and also benign, each of which maximizes his individual utility of the allocated resources minus his payment to the network operator. However, in many applications a user can use his payment to reduce the utilities of his opponents, thus playing a misbehaving role. It remains mysterious to what extent the misbehaving user can damage or influence the performance of benign users and the network operator. In this work, we formulate a non-cooperative game consisting of a finite amount of benign users and one misbehaving user. The maliciousness of this misbehaving user is captured by his willingness to pay to trade for unit degradation in the utilities of benign users. The network operator allocates resources to all the users via the price-anticipating Kelly mechanism. We present six important performance metrics with regard to the total utility and the total net utility of benign users, and the revenue of network operator under three different scenarios: with and without the misbehaving user, and the maximum. We quantify the robustness of PAKM against the misbehaving actions by deriving the upper and lower bounds of these metrics. With new approaches, all the theoretical bounds are applicable to an arbitrary population of benign users. Our study reveals two important insights: i) the performance bounds are very sensitive to the misbehaving user's willingness to pay at certain ranges; ii) the network operator acquires more revenues in the presence of the misbehaving user which might disincentivize his countermeasures against the misbehaving actions.

cs.SI↗

arXiv2021

Towards Performance Clarity of Edge Video Analytics

Edge video analytics is becoming the solution to many safety and management tasks. Its wide deployment, however, must first address the tension between inference accuracy and resource (compute/network) cost. This has led to the development of video analytics pipelines (VAPs), which reduce resource cost by combining DNN compression/speedup techniques with video processing heuristics. Our measurement study on existing VAPs, however, shows that today's methods for evaluating VAPs are incomplete, often producing premature conclusions or ambiguous results. This is because each VAP's performance varies substantially across videos and time (even under the same scenario) and is sensitive to different subsets of video content characteristics. We argue that accurate VAP evaluation must first characterize the complex interaction between VAPs and video characteristics, which we refer to as VAP performance clarity. We design and implement Yoda, the first VAP benchmark to achieve performance clarity. Using primitive-based profiling and a carefully curated benchmark video set, Yoda builds a performance clarity profile for each VAP to precisely define its accuracy/cost tradeoff and its relationship with video characteristics. We show that Yoda substantially improves VAP evaluations by (1) providing a comprehensive, transparent assessment of VAP performance and its dependencies on video characteristics; (2) explicitly identifying fine-grained VAP behaviors that were previously hidden by large performance variance; and (3) revealing strengths/weaknesses among different VAPs and new design opportunities.

cs.PF↗

arXiv2020

Et Tu Alexa? When Commodity WiFi Devices Turn into Adversarial Motion Sensors

Our work demonstrates a new set of silent reconnaissance attacks, which leverages the presence of commodity WiFi devices to track users inside private homes and offices, without compromising any WiFi network, data packets, or devices. We show that just by sniffing existing WiFi signals, an adversary can accurately detect and track movements of users inside a building. This is made possible by our new signal model that links together human motion near WiFi transmitters and variance of multipath signal propagation seen by the attacker sniffer outside of the property. The resulting attacks are cheap, highly effective, and yet difficult to detect. We implement the attack using a single commodity smartphone, deploy it in 11 real-world offices and residential apartments, and show it is highly effective. Finally, we evaluate potential defenses, and propose a practical and effective defense based on AP signal obfuscation.

cs.CR↗

arXiv2018

Addressing Training Bias via Automated Image Annotation

Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization, working in unison with cameras, can produce automated annotation of targets on images and videos captured in the wild. Using pedestrian and vehicle detection as examples, we demonstrate the feasibility, benefits, and challenges of an automatic image annotation system. Our work calls for new technical development on passive localization, mobile data analytics, and error-resilient ML models, as well as design issues in user privacy policies.

cs.CV↗

arXiv2016

Modeling QoE of Video Streaming in Wireless Networks with Large-Scale Measurement of User Behavior

Unraveling quality of experience (QoE) of video streaming is very challenging in bandwidth shared wireless networks. It is unclear how QoE metrics such as starvation probability and buffering time interact with dynamics of streaming traffic load. In this paper, we collect view records from one of the largest streaming providers in China over two weeks and perform an in-depth measurement study on flow arrival and viewing time that shed light on the real traffic pattern. Our most important observation is that the viewing time of streaming users fits a hyper-exponential distribution quite well. This implies that all the views can be categorized into two classes, short and long views with separated time scales. We then map the measured traffic pattern to bandwidth shared cellular networks and propose an analytical framework to compute the closed-form starvation probability on the basis of ordinary differential equations (ODEs). Our framework can be naturally extended to investigate practical issues including the progressive downloading and the finite video duration. Extensive trace-driven simulations validate the accuracy of our models. Our study reveals that the starvation metrics of the short and long views possess different sensitivities to the scheduling priority at base station. Hence, a better QoE tradeoff between the short and long views has a potential to be leveraged by offering them different scheduling weights. The flow differentiation involves tremendous technical and non-technical challenges because video content is owned by content providers but not the network operators and the viewing time of each session is unknown beforehand. To overcome these difficulties, we propose an online Bayesian approach to infer the viewing time of each incoming flow with the "least" information from content providers.

cs.NI↗