Sold by: MphasisÂ
Deployed on AWS
This solution enables users to custom define the sensitive information and automatically redact them using LLM based in-context reasoning.
Overview
This solution uses a finetuned Phi3.5 small Language Model (SLM) to identify sensitive information, that support redaction decisions which are grounded in document semantics. The system produces a redacted document and a rule trace that support audit of privacy compliance and validation by the reviewer. This solution takes as input the original document from user (that need sensitive data redaction) and a list of rules according to which the user wants to redact information. The input document content is chunked into smaller paragraphs and the rules are reasoned over the respective paragraph to redact the sensitive information. The solution output a final redacted document combining all the chunks into a single document and gives explanation for redaction. It helps organization to protect sensitive information and enable them to adhere to various Regulatory frameworks like GDPR, HIPPA etc.
Highlights
- A unique and easy-to-use solution for user defining, identifying and redacting any type of sensitive information in a document using a carefully finetuned phi-3.5 model. This solution protects the sensitive information organization data and enables them to adhere to various regulatory frameworks like GDPR, HIPPA etc. The relevant metrics to evaluate the performance of redaction with respect to privacy attacks are presented enabling data officers to quantify the data privacy.
- With the increase in digitization of personal and corporate communication, the automatic sanitization of textual data has become a crucial component to ensure data privacy and compliance at scale. Our finetuned SLM model automate this process of redaction and attack privacy by using a rule reasoning-based text sanitization. This solution involves minimum manual intervention and can handle high volume data redaction incurring reduced cost of redaction.
- Mphasis DeepInsights is a cloud-based cognitive computing platform that offers data extraction & predictive analytics capabilities. Need Customized Deep learning and Machine 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 |
|---|---|---|
ml.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $0.00/host/hour |
ml.g5.4xlarge Training Recommended | Algorithm training on the ml.g5.4xlarge instance type | $2.00/host/hour |
ml.m5.xlarge Inference (Batch) | Model inference on the ml.m5.xlarge instance type, batch mode | $0.00/host/hour |
ml.m5.2xlarge Inference (Batch) | Model inference on the ml.m5.2xlarge instance type, batch mode | $0.00/host/hour |
ml.m5.4xlarge Inference (Batch) | Model inference on the ml.m5.4xlarge instance type, batch mode | $0.00/host/hour |
ml.m5.12xlarge Inference (Batch) | Model inference on the ml.m5.12xlarge instance type, batch mode | $0.00/host/hour |
ml.m5.24xlarge Inference (Batch) | Model inference on the ml.m5.24xlarge instance type, batch mode | $0.00/host/hour |
ml.m4.xlarge Inference (Batch) | Model inference on the ml.m4.xlarge instance type, batch mode | $0.00/host/hour |
ml.m4.2xlarge Inference (Batch) | Model inference on the ml.m4.2xlarge instance type, batch mode | $0.00/host/hour |
ml.m4.4xlarge Inference (Batch) | Model inference on the ml.m4.4xlarge instance type, batch mode | $0.00/host/hour |
Vendor refund policy
We do not have any refund policy
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)Â .
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
v1
Additional details
Inputs
- Summary
The model input is a zip file which consists of two pdfs:
- The original document that needs to be redacted
- The rules file consisting of natural language rules in accordance to which sensitive data is redacted.
- Limitations for input type
- Do not enter more than 3 rules in one run
https://github.com/MphasisLimited/AWSMarketplace/blob/main/Responsible%20AI%20Data%20Privacy%20Automation/data/test_redaction.zip
https://github.com/MphasisLimited/AWSMarketplace/blob/main/Responsible%20AI%20Data%20Privacy%20Automation/data/test_redaction.zip
Support
Vendor support
For any assistance 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
Securonix is leading the transformation of cybersecurity with the Unified Defense SIEM powered by agentic AI and built natively on AWS and Snowflake. By leveraging Amazon Bedrock for advanced AI agents and a split-data architecture, Securonix delivers elastic, privacy-preserving analytics that keep telemetry where customers want it while cutting storage costs and accelerating detection. Our platform collects and correlates logs across AWS services and applies behavioral analytics and AI-driven threat models and automates response with built-in SOAR to provide end-to-end visibility for containerized workloads and hybrid environments. Recognized as a 6x Leader in the Gartner® Magic Quadrant™ for SIEM and a 2x Customers Choice by Gartner Peer Insights™, Securonix empowers organizations to move from reactive security to proactive, autonomous operations.
baioniq is an enterprise-grade generative AI platform that helps organizations harness the power of large language models (LLMs) within their secure AWS environment. It enables businesses to build, customize, and deploy AI solutions that understand their unique domain context while maintaining data privacy and security. The platform seamlessly integrates with Amazon Bedrock and SageMaker, allowing organizations to fine-tune models for specific use cases, automate workflows, and drive operational efficiency.
Collibra Data Intelligence Platform enables organizations to do more with trusted data and accelerate positive business outcomes by delivering accurate data for every use, for every user, and across every source. Collibra Data Intelligence Platform provides a single platform for data management helping to unlock your data to solve problems, accelerate business outcomes, fuel your AI strategy and build a data-driven culture
baioniq is an enterprise-grade generative AI platform that helps organizations harness the power of large language models (LLMs) within their secure AWS environment. It enables businesses to build, customize, and deploy AI solutions that understand their unique domain context while maintaining data privacy and security. The platform seamlessly integrates with Amazon Bedrock and SageMaker, allowing organizations to fine-tune models for specific use cases, automate workflows, and drive operational efficiency.
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.