Pub

publications by categories in reversed chronological order. generated by jekyll-scholar.

2023

  1. Neural network activation compression with non-uniform mantissas
    Daniel Lo, Amar Phanishayee, Eric S Chung, and 1 more author
    Jan 2023
    US Patent 11,562,247
  2. Architectural backdoors in neural networks
    Mikel Bober-Irizar, Ilia Shumailov, Yiren Zhao, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jan 2023
  3. Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
    Xiangyu Zhao, Hannes Stärk, Dominique Beaini, and 2 more authors
    arXiv preprint arXiv:2301.11517, Jan 2023
  4. Dynamic Stashing Quantization for Efficient Transformer Training
    Guo Yang, Daniel Lo, Robert Mullins, and 1 more author
    arXiv preprint arXiv:2303.05295, Jan 2023
  5. Revisiting Automated Prompting: Are We Actually Doing Better?
    Yulin Zhou, Yiren Zhao, Ilia Shumailov, and 2 more authors
    arXiv preprint arXiv:2304.03609, Jan 2023
  6. NEURAL NETWORK ACTIVATION COMPRESSION WITH NON-UNIFORM MANTISSAS
    Daniel Lo, Amar Phanishayee, Eric S Chung, and 1 more author
    May 2023
    US Patent App. 18/092,876
  7. Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity
    Dongping Liao, Xitong Gao, Yiren Zhao, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, May 2023
  8. Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs
    Zehui Li, Xiangyu Zhao, Mingzhu Shen, and 3 more authors
    arXiv preprint arXiv:2306.05108, May 2023
  9. Genomic Interpreter: A Hierarchical Genomic Deep Neural Network with 1D Shifted Window Transformer
    Zehui Li, Akashaditya Das, William AV Beardall, and 2 more authors
    arXiv preprint arXiv:2306.05143, May 2023
  10. The Curse of Recursion: Training on Generated Data Makes Models Forget
    Ilia Shumailov, Zakhar Shumaylov, Yiren Zhao, and 3 more authors
    arXiv preprint arxiv:2305.17493, May 2023
  11. Fast Prototyping Next-Generation Accelerators for New ML Models using MASE: ML Accelerator System Exploration
    Jianyi Cheng, Cheng Zhang, Zhewen Yu, and 4 more authors
    arXiv preprint arXiv:2307.15517, May 2023
  12. Will More Expressive Graph Neural Networks do Better on Generative Tasks?
    Xiandong Zou, Xiangyu Zhao, Pietro Liò, and 1 more author
    arXiv preprint arXiv:2308.11978, May 2023

2022

  1. DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
    Robert Hönig, Yiren Zhao, and Robert Mullins
    In International Conference on Machine Learning, May 2022
  2. Model Architecture Adaption for Bayesian Neural Networks
    Duo Wang, Yiren Zhao, Ilia Shumailov, and 1 more author
    arXiv preprint arXiv:2202.04392, May 2022
  3. Efficient Adversarial Training With Data Pruning
    Maximilian Kaufmann, Yiren Zhao, Ilia Shumailov, and 2 more authors
    arXiv preprint arXiv:2207.00694, May 2022
  4. Software and Hardware Co-design for Efficient Neural Networks
    Aaron Zhao
    University of Cambridge, May 2022
  5. Augmentation Backdoors
    Joseph Rance, Yiren Zhao, Ilia Shumailov, and 1 more author
    arXiv preprint arXiv:2209.15139, May 2022
  6. ImpNet: Imperceptible and blackbox-undetectable backdoors in compiled neural networks
    Eleanor Clifford, Ilia Shumailov, Yiren Zhao, and 2 more authors
    arXiv preprint arXiv:2210.00108, May 2022
  7. Wide Attention Is The Way Forward For Transformers
    Jason Ross Brown, Yiren Zhao, Ilia Shumailov, and 1 more author
    arXiv preprint arXiv:2210.00640, May 2022
  8. DARTFormer: Finding The Best Type Of Attention
    Jason Ross Brown, Yiren Zhao, Ilia Shumailov, and 1 more author
    arXiv preprint arXiv:2210.00641, May 2022
  9. Revisiting Structured Dropout
    Yiren Zhao, Oluwatomisin Dada, Xitong Gao, and 1 more author
    arXiv preprint arXiv:2210.02570, May 2022
  10. Revisiting Embeddings for Graph Neural Networks
    Skye Purchase, Yiren Zhao, and Robert D Mullins
    In Learning on Graphs Conference, May 2022
  11. Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation
    Tianrui Qin, Xianghuan He, Xitong Gao, and 3 more authors
    arXiv preprint arXiv:2212.09979, May 2022
  12. Rapid Model Architecture Adaption for Meta-Learning
    Yiren Zhao, Xitong Gao, Ilia Shumailov, and 2 more authors
    In Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), May 2022

2021

  1. Sponge examples: Energy-latency attacks on neural networks
    Ilia Shumailov, Yiren Zhao, Daniel Bates, and 3 more authors
    In 2021 IEEE European Symposium on Security and Privacy (EuroS&P), May 2021
  2. Manipulating sgd with data ordering attacks
    Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan, and 4 more authors
    Advances in Neural Information Processing Systems, May 2021
  3. Markpainting: Adversarial Machine Learning meets Inpainting
    David Khachaturov, Ilia Shumailov, Yiren Zhao, and 2 more authors
    In 38th International Conference on Machine Learning, May 2021
  4. FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning
    Dongping Liao, Xitong Gao, Yiren Zhao, and 6 more authors
    May 2021

2020

  1. Blackbox attacks on reinforcement learning agents using approximated temporal information
    Yiren Zhao, Ilia Shumailov, Han Cui, and 3 more authors
    In 2020 50th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), May 2020
  2. Towards certifiable adversarial sample detection
    Ilia Shumailov, Yiren Zhao, Robert Mullins, and 1 more author
    In Proceedings of the 13th ACM Workshop on Artificial Intelligence and Security, May 2020
  3. Pay Attention to Features, Transfer Learn Faster CNNs
    Kafeng Wang, Xitong Gao, Yiren Zhao, and 3 more authors
    In International Conference on Learning Representations, May 2020
  4. Probabilistic Dual Network Architecture Search on Graphs
    Yiren Zhao, Duo Wang, Xitong Gao, and 3 more authors
    arXiv preprint arXiv:2003.09676, May 2020
  5. Learned Low Precision Graph Neural Networks
    Yiren Zhao, Duo Wang, Daniel Bates, and 3 more authors
    arXiv preprint arXiv:2009.09232, May 2020
  6. Nudge Attacks on Point-Cloud DNNs
    Yiren Zhao, Ilia Shumailov, Robert Mullins, and 1 more author
    arXiv preprint arXiv:2011.11637, May 2020
  7. Adjusting activation compression for neural network training
    Daniel Lo, Bita Darvish Rouhani, Eric S Chung, and 3 more authors
    Aug 2020
    US Patent App. 16/276,395
  8. Neural network activation compression with narrow block floating-point
    Daniel Lo, Amar Phanishayee, Eric S Chung, and 2 more authors
    Jul 2020
    US Patent App. 16/237,197
  9. Neural network activation compression with outlier block floating-point
    Daniel Lo, Amar Phanishayee, Eric S Chung, and 2 more authors
    Jul 2020
    US Patent App. 16/237,202

2019

  1. Dynamic Channel Pruning: Feature Boosting and Suppression
    Xitong Gao, Yiren Zhao, Lukasz Dudziak, and 2 more authors
    In International Conference on Learning Representations (ICLR), Jul 2019
  2. Sitatapatra: Blocking the Transfer of Adversarial Samples
    Ilia Shumailov, Xitong Gao, Yiren Zhao, and 3 more authors
    arXiv preprint arXiv:1901.08121, Jul 2019
  3. Focused quantization for sparse CNNs
    Yiren Zhao, Xitong Gao, Daniel Bates, and 2 more authors
    In Advances in Neural Information Processing Systems, Jul 2019
  4. Characterizing Sources of Ineffectual Computations in Deep Learning Networks
    Miloš Nikolić, Mostafa Mahmoud, Andreas Moshovos, and 2 more authors
    In 2019 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Jul 2019
  5. Automatic generation of multi-precision multi-arithmetic CNN accelerators for FPGAs
    Yiren Zhao, Xitong Gao, Xuan Guo, and 6 more authors
    In 2019 International Conference on Field-Programmable Technology (ICFPT), Jul 2019

2018

  1. Redundancy-reduced mobilenet acceleration on reconfigurable logic for imagenet classification
    Jiang Su, Julian Faraone, Junyi Liu, and 4 more authors
    In Applied Reconfigurable Computing. Architectures, Tools, and Applications: 14th International Symposium, ARC 2018, Santorini, Greece, May 2-4, 2018, Proceedings 14, Jul 2018
  2. Mayo: A Framework for Auto-generating Hardware Friendly Deep Neural Networks
    Yiren Zhao, Xitong Gao, Robert Mullins, and 1 more author
    In Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning (EMDL 2018), Jul 2018
  3. To compress or not to compress: Understanding the Interactions between Adversarial Attacks and Neural Network Compression
    Yiren Zhao, Ilia Shumailov, Robert Mullins, and 1 more author
    In The Conference on Systems and Machine Learning (SysML), Jul 2018
  4. The Taboo Trap: Behavioural Detection of Adversarial Samples
    Ilia Shumailov, Yiren Zhao, Robert Mullins, and 1 more author
    arXiv preprint arXiv:1811.07375, Jul 2018

2016

  1. An efficient implementation of online arithmetic
    Yiren Zhao, John Wickerson, and George A Constantinides
    In 2016 International Conference on Field-Programmable Technology (FPT), Jul 2016