
A New Frontier in AI: Training AI Applications Using Sensitive Information and the Potential Data Privacy Risks Involved (RECORDING)
-
You must log in to register
- Non-member - $150
- Member - Free!
Recently, companies have built a new frontier of AI applications that perform predictive tasks using sensitive information. For example, today there are AI applications that predict a patient’s health issues or infer the next sentence to write in a private email. Building AI applications by training AI models with sensitive information, however, presents significant data privacy risks. If improperly trained, an AI model can unintentionally “memorize” rare or unique sensitive information included in a large set of training data. This creates the risk that the AI model will disclose the sensitive information “as-is” in response to new, previously unseen input data. This is particularly problematic for AI applications that are widely used by the public because hackers can exploit this vulnerability to extract the sensitive information. Hackers can input different prefixed texts to “inferentially attack” an improperly trained AI application to extract the sensitive information that was included in the training data set during the training process. This unintended “memorization” is also a threat to AI models trained to infer word associations from a business’s internal information. A simple inference of uncommon word combinations from the business’s internal information can reveal trade secrets.
This webinar will describe the issues involved with training AI models using sensitive information. Attendees will also learn about the data privacy risks and legal implications that arise when AI models are trained using sensitive information. Lastly, this webinar will discuss data science techniques that can prevent the problem of “unintended memorization.”
Anthony Glosson
Kilpatrick, Townsend & Stockton LLP
Anthony Glosson of Kilpatrick Townsend, focuses his practice on cybersecurity, privacy, risk management, and regulatory compliance matters. Tony is the author of several publications in the field of technology law and regularly dives into the technical aspects of enterprise network security, business continuity, and incident response.
Sameer Vadera
Kilpatrick, Townsend & Stockton LLP
Sameer Vadera is a patent attorney with Kilpatrick Townsend who counsels industry-leading clients on building valuable IP portfolios for high-tech innovations. He has managed domestic and global patent portfolios, driven IP protection strategies across major markets, and counseled enterprises on boosting IP assets by increasing enterprise-wide innovation capture. Mr. Vadera has prepared and prosecuted patent applications directed to a wide range of technologies, including machine learning and artificial intelligence, Blockchain, and network security. Additionally, Mr. Vadera frequently publishes and presents on data ownership and data privacy issues in the context of artificial intelligence. Mr. Vadera is also a co-founder of Triangle IP, LLC, an AI-powered innovation management platform that intelligently assists enterprises with efficiently building IP portfolios.
Key:




