公开(公告)号：US20240045974A1

公开(公告)日：2024-02-08

申请号：US18382107

申请日：2023-10-20

Applicant: International Business Machines Corporation

Inventor： Pin-Yu Chen ,  Sijia Liu ,  Lingfei Wu ,  Chia-Yu Chen

IPC: G06F21/57 ,  G06N3/04 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06F21/577 ,  G06N3/04 ,  G06N3/08 ,  G06V10/764 ,  G06V10/82 ,  G06F2221/034

Abstract: An adversarial robustness testing method, system, and computer program product include testing, via an accelerator, a robustness of a black-box system under different access settings, where the testing includes tearing down the robustness testing to a subtask of a predetermined size.

公开(公告)号：US11763084B2

公开(公告)日：2023-09-19

申请号：US16989882

申请日：2020-08-10

Applicant: International Business Machines Corporation

Inventor： Dakuo Wang ,  Arunima Chaudhary ,  Chuang Gan ,  Mo Yu ,  Qian Pan ,  Sijia Liu ,  Daniel Karl I. Weidele ,  Abel Valente

IPC: G06F40/289 ,  G06N20/00 ,  G06N5/04

CPC classification number: G06F40/289 ,  G06N5/04 ,  G06N20/00

Abstract: A method comprises receiving a new data set; identifying at least one prior data set of a plurality of prior data sets that matches the new data set; generating a natural language data science problem statement for the new data set based on information associated with the at least prior one data set that matches the new data set; outputting the generated natural language data science problem statement for user verification; and in response to receiving user input verifying the natural language generated data science problem statement, generating one or more AutoAI configuration settings for the new data set based on one or more AutoAI configuration settings associated with the at least one prior data set that matches the new data set.

公开(公告)号：US20230004754A1

公开(公告)日：2023-01-05

申请号：US17363043

申请日：2021-06-30

Applicant: International Business Machines Corporation

Inventor： Quanfu Fan ,  Sijia Liu ,  GAOYUAN ZHANG ,  Kaidi Xu

IPC: G06K9/62 ,  G06N20/00 ,  G06F3/12

Abstract: Adversarial patches can be inserted into sample pictures by an adversarial image generator to realistically depict adversarial images. The adversarial image generator can be utilized to train an adversarial patch generator by inserting generated patches into sample pictures, and submitting the resulting adversarial images to object detection models. This way, the adversarial patch generator can be trained to generate patches capable of defeating object detection models.

公开(公告)号：US11416775B2

公开(公告)日：2022-08-16

申请号：US16851221

申请日：2020-04-17

Applicant: International Business Machines Corporation

Inventor： Pin-yu Chen ,  Sijia Liu ,  Shiyu Chang ,  Payel Das ,  Minhao Cheng

IPC: G06N20/00 ,  G06F17/18

Abstract: Techniques for training robust machine learning models for adversarial input data. Training data for a machine learning (ML) model is received. The training data includes a plurality of labels for data elements. First modified training data is generated by modifying one or more of the plurality of labels in the training data using parameterized label smoothing with a first optimization parameter. The ML model is trained using the first modified training data. The training includes updating a first one or more model weights in the ML model, and generating a second optimization parameter suitable for use in future parameterized label smoothing for future training of the ML model

公开(公告)号：US20220101120A1

公开(公告)日：2022-03-31

申请号：US17039989

申请日：2020-09-30

Applicant: International Business Machines Corporation ,  Massachusetts Institute of Technology

Inventor： Dakuo Wang ,  Sijia Liu ,  Abel Valente ,  Chuang Gan ,  Bei Chen ,  Dongyu Liu ,  Yi Sun

IPC: G06N3/08 ,  G06N3/04

Abstract: Use a computerized trained graph neural network model to classify an input instance with a predicted label. With a computerized graph neural network interpretation module, compute a gradient-based saliency matrix based on the input instance and the predicted label, by taking a partial derivative of class prediction with respect to an adjacency matrix of the model. With a computerized user interface, obtain user input responsive to the gradient-based saliency matrix. Optionally, modify the trained graph neural network model based on the user input; and re-classify the input instance with a new predicted label based on the modified trained graph neural network model.

公开(公告)号：US11276419B2

公开(公告)日：2022-03-15

申请号：US16526990

申请日：2019-07-30

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Yang Zhang ,  Chuang Gan ,  Sijia Liu ,  Dakuo Wang

IPC: G10L25/57 ,  G10L25/30 ,  G06N3/04 ,  H04N21/81 ,  H04N21/845

Abstract: A computing device receives a video feed. The video feed is divided into a sequence of video segments. For each video segment, visual features of the video segment are extracted. A predicted spectrogram is generated based on the extracted visual features. A synthetic audio waveform is generated from the predicted spectrogram. All synthetic audio waveforms of the video feed are concatenated to generate a synthetic soundtrack that is synchronized with the video feed.

公开(公告)号：US20220076144A1

公开(公告)日：2022-03-10

申请号：US17015243

申请日：2020-09-09

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Parikshit Ram ,  Dakuo Wang ,  Deepak Vijaykeerthy ,  Vaibhav Saxena ,  Sijia Liu ,  Arunima Chaudhary ,  Gregory Bramble ,  Horst Cornelius Samulowitz ,  Alexander Gray

IPC: G06N5/04 ,  G06K9/62 ,  G06F9/38

Abstract: The exemplary embodiments disclose a method, a computer program product, and a computer system for determining that one or more model pipelines satisfy one or more constraints. The exemplary embodiments may include detecting a user uploading data, one or more constraints, and one or more model pipelines, collecting the data, the one or more constraints, and the one or more model pipelines, and determining that one or more of the model pipelines satisfies all of the one or more constraints based on applying one or more algorithms to the collected data, constraints, and model pipelines.

公开(公告)号：US20210383497A1

公开(公告)日：2021-12-09

申请号：US16894343

申请日：2020-06-05

Applicant: International Business Machines Corporation ,  Rensselaer Polytechnic Institute

Inventor： Ao Liu ,  Sijia Liu ,  Abhishek Bhandwaldar ,  Chuang Gan ,  Lirong Xia ,  Qi Cheng Li

IPC: G06T1/00 ,  G06T5/00 ,  G06T5/20 ,  G06T5/50 ,  G06N3/02

Abstract: Interpretation maps of deep neural networks are provided that use Renyi differential privacy to guarantee the robustness of the interpretation. In one aspect, a method for generating interpretation maps with guaranteed robustness includes: perturbing an original digital image by adding Gaussian noise to the original digital image to obtain m noisy images; providing the m noisy images as input to a deep neural network; interpreting output from the deep neural network to obtain m noisy interpretations corresponding to the m noisy images; thresholding the m noisy interpretations to obtain a top-k of the m noisy interpretations; and averaging the top-k of the m noisy interpretations to produce an interpretation map with certifiable robustness.

公开(公告)号：US20210064785A1

公开(公告)日：2021-03-04

申请号：US16559161

申请日：2019-09-03

Applicant: International Business Machines Corporation

Inventor： Sijia Liu ,  Quanfu Fan ,  Gaoyuan Zhang ,  Chuang Gan

IPC: G06F21/71 ,  G06F21/57 ,  G06N20/00

Abstract: An illustrative embodiment includes a method for protecting a machine learning model. The method includes: determining concept-level interpretability of respective units within the model; determining sensitivity of the respective units within the model to an adversarial attack; identifying units within the model which are both interpretable and sensitive to the adversarial attack; and enhancing defense against the adversarial attack by masking at least a portion of the units identified as both interpretable and sensitive to the adversarial attack.

公开(公告)号：US20200242507A1

公开(公告)日：2020-07-30

申请号：US16257965

申请日：2019-01-25

Applicant: International Business Machines Corporation

Inventor： Chuang Gan ,  Quanfu Fan ,  Sijia Liu ,  Rogerio Schmidt Feris

IPC: G06N20/00 ,  H04N21/4402 ,  H04N21/439 ,  G06N3/08

Abstract: A computing system is configured to learn data-augmentations from unlabeled media. The system includes an extracting unit and an embedding unit. The extracting unit is configured to receive media data that includes moving images of an object and audio generated by the object. The extracting unit extracts an image frame of the object among the moving images and extracts an audio segment from the audio. The embedding unit is configured to generate first embeddings of the image frame and second embeddings of the audio segment, and to concatenate the first and second embeddings together to generate concatenated embeddings. The computing system labels the media data based at least in part on the concatenated embeddings.