Sold by: Mphasis
Deployed on AWS
The solution measures the robustness of an image classifier against model inversion attack while having black box access to the classifier
Overview
As machine learning models gain prominence in various enterprise applications, privacy of data has become a growing concern. Model inversion attacks aim to infer sensitive information about data by exploiting the model's output. This is achieved by iteratively guessing the exact input data features based on the model's outputs. For example, if a model is trained to predict a person's income based on their education, experience, and other factors, an attacker can use the model's output (predicted income) to infer the person's education, experience, and other sensitive information. This solution takes an image classifier and gives the robustness of this classifier against model inversion attack.
Highlights
- The solution evaluates the model's vulnerability to inversion attack by simulating the attack and analyzing the model's output. To simulate the attack, user needs to input the target class label to be attacked. The solution generates images of target class and calculates the similarity of these images with actual image of that class. These similarities show the robustness of model against model inversion attack against the target class. The higher similiarity scores indicates the lesser robustness of model against inversion attack.
- The solution requires the keras model file of Image classifier and the original image of target class. The solution performs black box attack on the model i.e, only the model's ouput is accessible, and, not the internals of the model. The user can control the number of iterations of gradient computations to be performed to generate image of desired class. The similarity score of generated image to the acutal image of the target class measures the model vulnerability.
- PACE - ML is Mphasis Framework and Methodology for end-to-end machine learning development and deployment. PACE-ML enables organizations to improve the quality & reliability of the machine learning solutions in production and helps automate, scale, and monitor them. Need customized Machine Learning and Deep Learning solutions? Get in touch!
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $0.00 |
ml.m5.large Inference (Real-Time) Recommended | Model inference on the ml.m5.large instance type, real-time mode | $0.00 |
ml.m5.large Training Recommended | Algorithm training on the ml.m5.large instance type | $10.00 |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $0.00 |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $0.00 |
ml.m4.16xlarge Inference (Batch) | Model inference on the ml.m4.16xlarge instance type, batch mode | $0.00 |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $0.00 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $0.00 |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $0.00 |
ml.c5.2xlarge Inference (Batch) | Model inference on the ml.c5.2xlarge instance type, batch mode | $0.00 |
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to the service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This is the first version.
Additional details
Inputs
- Summary
The solution takes trained model to query, the actual image of target class and some parameters in parameters.json file.
- Input MIME type
- text/csv
https://github.com/Mphasis-ML-Marketplace/ML-Robustness-Model-Inversion-attack/tree/main/input
https://github.com/Mphasis-ML-Marketplace/ML-Robustness-Model-Inversion-attack/tree/main/input
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
parameters.json | “parameters.json” contains key value pair. Keys and their descriptions are as follows:
“class_to_attack”: The class label which you want to target and generate/replicate images of that class.
“learning_rate”: learning rate for the algorithm to replicate target class image.
“iterations”: list of number of iterations to be performed to replicate image
“initialization”: initialization of image out of ‘white’,’grey’,’random’ and ‘black’ | Type: Continuous | Yes |
Resources
Vendor resources
Support
Vendor support
For any product support you can reach out to us at:
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Looking to launch your first ML project on AWS? Want to know how to increase the impact of your existing AI/ML offering? Our Advanced Consulting ML and Data specialists will conduct a free 60-90 minute strategy session to help you better understand how to leverage ML, data and AWS services to drive business efficiency and power intelligent apps.
1-hour discovery or project scoping session with personalized insights and strategic recommendations from industry-leading professionals
SnapSoft's complimentary AI/ML workshop provides essential knowledge, guidance, and skills to build a robust infrastructure and implement an efficient AI/ML strategy using various AWS services.
DuploCloud offers a free AI/ML workshop, providing essential guidance and expertise to shape your AI strategy and leverage AWS services effectively for innovation and efficiency.
Pre-configured AMI with Python, CUDA Toolkit, and JupyterLab for seamless development. Ideal for developers and data scientists who need a ready-to-use environment for GPU-accelerated workflows, machine learning, and data analysis without the hassle of manual setup.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.