Xingbin Wang

Prof. Xingbin Wang

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 January 2025
Verified
Conference Paper
Open access
YWYan Wang
Yan Wang
Xingbin WangXingbin Wang
Xingbin Wang
YSYulan Su
Yulan Su
SZSisi Zhang
Sisi Zhang
ZLZechao Lin
Zechao Lin
RHRui Hou
Rui Hou
Robust variants represent a promising method to enhance model robustness against adversarial attacks through exploring diverse neural network architectures. However, the significant computational demand of training multiple variants often restricts adversarial defense techniques to a narrow range of model architectures, thus failing to fully exploit the robustness benefits of architectural variations. In this paper, we first reveal that function-preserving knowledge transfer can significantly speed up adversarial training of different architecture variants. Then, we propose ROBIN, a framework for accelerating adversarially robust multi-variant training. By utilizing the architectural similarities among variants, ROBIN facilitates efficient weight transformation across models via two tensor-level atomic operations, hastening the convergence of multiple variants. Our experiments indicate that ROBIN can accelerate the adversarial training process of various architecture variants by 2.56 × to 4.27 ×, enabling efficient exploration of robust network architectures.

23 June 2024
Verified
Conference Paper
Open access
YWYan Wang
Yan Wang
Xingbin WangXingbin Wang
Xingbin Wang
ZLZechao Lin
Zechao Lin
YSYulan Su
Yulan Su
SZSisi Zhang
Sisi Zhang
DMDan Meng
Dan Meng
In the face of huge threats from adversarial attacks, developing an efficient defense mechanism is crucial for deep learning systems. Adversarial ensemble defense method is one of the most effective techniques for defending against adversarial attacks, which constructs ensembles of multiple DNNs to improve model's robustness. However, deploying ensemble defense methods on existing DNN inference systems is inefficient and impractical due to their dynamics and randomness. To this end, we propose an inference system for adversarial ensemble defense called Garrison, which can deliver robust and low-latency predictions using Multi-Instance GPUs. Garrison employs a multi-granularity GPU partitioning strategy, optimizing hardware utilization by capitalizing on the intrinsic heterogeneity of GPUs. It also integrates a reinforcement learning-based scheduling mechanism, enabling random ensemble of diverse defense models to enhance robustness while maintaining bounded latency. Our evaluations show that Garrison can improve adversarial robustness by up to 24.5%, while accelerating ensemble inference by up to 6.6X compared to the state-of-the-art inference framework.

16 April 2024 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
Xingbin WangXingbin Wang
Xingbin Wang
YWYan Wang
Yan Wang
YSYulan Su
Yulan Su
SZSisi Zhang
Sisi Zhang
DMDan Meng
Dan Meng
RHRui Hou
Rui Hou
To defend against various adversarial attacks, it is essential to develop a robust and high computing efficiency defence framework. Adversarial ensemble learning is the most effective technique for defending against adversarial example attacks, which constructs ensembles of multiple Deep neural networks (DNNs) with adversarial training to obtain stronger defense. However, ensemble models run noticeably slower on existing DNN accelerators than single-model inference. Deploying ensemble models on the existing DNN accelerators leads to many critical issues such as the underutilization of hardware resources. To tackle emerging challenges, we propose EnsGuard, a dynamic asymmetric multicore systolic array architecture for adversarial ensemble learning inference to fully exploit both static and dynamic parallelism of ensemble models. Specifically, on the hardware level, we propose a novel instruction set extension and develop efficient architecture components to fully exploit the new hardware abstraction of scattered idle computing cores, and use them to dynamically create on-the-fly neural processing units (fNPUs). Moreover, we propose a computing power recycle mechanism to run on-the-fly models (small models) on fNPUs by carefully orchestrating execution order of ensemble models for maximizing hardware resources and bandwidth utilization. On the software level, EnsGuard adopts an integrated hardware/randomized ensemble co-design optimizer aiming at winning both faster inference and higher adversarial robustness. On top of that, a multimodel mapping method based on decision tree is proposed to enable the interleaving of different DNN executions both spatially and temporally, and mitigate straggler problems. Evaluation with a diverse set of workloads shows significant gains in throughput ( $4.4\times $ ) and energy reduction ( $3.2\times $ ).

26 August 2024
Verified
Book Chapter
Closed access
PDF file
Xingbin WangXingbin Wang
Xingbin Wang
DMDan Meng
Dan Meng
RHRui Hou
Rui Hou
YWYan Wang
Yan Wang

23 June 2024
Verified
Conference Paper
Open access
YZYifan Zhu
Yifan Zhu
PLPeinan Li
Peinan Li
YBYunkai Bai
Yunkai Bai
YHYubiao Huang
Yubiao Huang
SWShiwen Wang
Shiwen Wang
RHRui Hou
Rui Hou
Serverless computing has gained widespread attention, and Trusted Execution Environments (TEEs) are well-suited for safeguarding user privacy. However, the additional startup procedure introduced by TEEs imposes considerable performance overhead on confidential serverless workloads. This paper introduces a novel parallelized enclave startup design, EnTurbo, which eliminates the integrity dependence of the enclave startup procedure, accelerating it while ensuring its security. Additionally, EnTurbo parallelizes the measurement procedure, enabling multi-thread measurement for acceleration with provable security. We evaluate EnTurbo by running confidential serverless workloads on SGX simulation mode. Results show that EnTurbo effectively speeds up enclave serverless by 1.42x-6.48x (SGXv1) and 1.33x-3.76x (SGXv2).