中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

40 records (took 0.019 seconds)

    ROBUSTNESS-AWARE QUANTIZATION FOR NEURAL NETWORKS AGAINST WEIGHT PERTURBATIONS
    4.
    发明申请
    ROBUSTNESS-AWARE QUANTIZATION FOR NEURAL NETWORKS AGAINST WEIGHT PERTURBATIONS 有权

    公开(公告)号：US20210334646A1

    公开(公告)日：2021-10-28

    申请号：US16861019

    申请日：2020-04-28

    Applicant: International Business Machines Corporation

    Inventor： Sijia Liu ,  Pin-Yu Chen ,  Gaoyuan Zhang ,  Chuang Gan

    IPC: G06N3/08 ,  G06N20/00 ,  G06F17/18

    Abstract: A method of utilizing a computing device to optimize weights within a neural network to avoid adversarial attacks includes receiving, by a computing device, a neural network for optimization. The method further includes determining, by the computing device, on a region by region basis one or more robustness bounds for weights within the neural network. The robustness bounds indicating values beyond which the neural network generates an erroneous output upon performing an adversarial attack on the neural network. The computing device further averages all robustness bounds on the region by region basis. The computing device additionally optimizes weights for adversarial proofing the neural network based at least in part on the averaged robustness bounds.

    Interpretability-Aware Adversarial Attack and Defense Method for Deep Learnings
    5.
    发明申请
    Interpretability-Aware Adversarial Attack and Defense Method for Deep Learnings 有权

    公开(公告)号：US20210216859A1

    公开(公告)日：2021-07-15

    申请号：US16742346

    申请日：2020-01-14

    Applicant: International Business Machines Corporation

    Inventor： Sijia Liu ,  Gaoyuan Zhang ,  Pin-Yu Chen ,  Chuang Gan ,  Akhilan Boopathy

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Embodiments relate to a system, program product, and method to support a convolutional neural network (CNN). A class-specific discriminative image region is localized to interpret a prediction of a CNN and to apply a class activation map (CAM) function to received input data. First and second attacks are generated on the CNN with respect to the received input data. The first attack generates first perturbed data and a corresponding first CAM, and the second attack generates second perturbed data and a corresponding second CAM. An interpretability discrepancy is measured to quantify one or more differences between the first CAM and the second CAM. The measured interpretability discrepancy is applied to the CNN. The application is a response to an inconsistency between the first CAM and the second CAM and functions to strengthen the CNN against an adversarial attack.

    Distributed Adversarial Training for Robust Deep Neural Networks
    9.
    发明申请
    Distributed Adversarial Training for Robust Deep Neural Networks 有权

    公开(公告)号：US20220261626A1

    公开(公告)日：2022-08-18

    申请号：US17170343

    申请日：2021-02-08

    Applicant: International Business Machines Corporation

    Inventor： Sijia Liu ,  Gaoyuan ZHANG ,  Pin-Yu Chen ,  Chuang Gan ,  Songtao Lu

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Scalable distributed adversarial training techniques for robust deep neural networks are provided. In one aspect, a method for adversarial training of a deep neural network-based model by distributed computing machines M includes, by distributed computing machines M: obtaining adversarial perturbation-modified training examples for samples in a local dataset D(i); computing gradients of a local cost function fi with respect to parameters θ of the deep neural network-based model using the adversarial perturbation-modified training examples; transmitting the gradients of the local cost function fi to a server which aggregates the gradients of the local cost function fi and transmits an aggregated gradient to the distributed computing machines M; and updating the parameters θ of the deep neural network-based model stored at each of the distributed computing machines M based on the aggregated gradient received from the server. A method for distributed adversarial training of a deep neural network-based model by the server is also provided.

Patent Agency Ranking