Privacy experts present new AI model to prevent data breaches at LA conference


Privacy experts attending the annual CCS conference in LA

Data privacy experts from Imperial presented their new AI model which helps prevent data breaches at the 29th ACM CCS Conference.

On 7 November 2022, privacy and security experts from all over the globe gathered for the annual ACM Conference on Computer and Communications Security, held this year in Los Angeles.

The ACM Conference on Computer and Communications Security (CCS) is the flagship annual conference of the Special Interest Group on Security, Audit and Control (SIGSAC) of the Association for Computing Machinery (ACM), and brings together information security researchers, practitioners, developers and users to explore cutting-edge ideas and results.

The conference was attended by Imperial’s Ana-Maria Cretu and Dr Florimond Houssiau, both current or former PhD students of the Computational Privacy Group at Imperial and the DSI. Dr Houssiau is now a Research Associate at the Alan Turing Institute. 

Ana-Maria Cretu presenting the QuerySnout AI model to help prevent data breaches
Ana-Maria Cretu presenting the QuerySnout AI model to help prevent data breaches

QuerySnout: An AI tool to help prevent damaging data breaches

Ana-Maria Cretu presented their recent paper on a new AI algorithm that automatically tests privacy-preserving systems for potential data leaks, called QuerySnout.

Through their research the experts, from Imperial’s Computational Privacy Group, looked at attacks on query-based systems (QBS) - controlled interfaces through which analysts can query data to extract useful aggregate information about the world. They then developed a new AI-enabled method to detect attacks on QBS.

QBS give analysts access to collections of statistics gathered from individual-level data like location and demographics. They are currently used in Google Maps to show live information on how busy an area is, or in Facebook's Audience Measurement feature to estimate audience size in a particular location or demographic to help with advertising promotions.

In their study, which they presented at the conference, the team found that powerful and accurate attacks against QBS can easily be automatically detected at the pressing of a button.

For more information on QuerySnout, you can read this Imperial News Story.


QuerySnout: Automating the Discovery of Attribute Interference Attacks against Query-Based Systems by A. M. Cretu, F. Houssiau, A. Cully and Y. A. de Montjoye, published on 7 November 2022 in Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security.


Gemma Ralton

Gemma Ralton
Faculty of Engineering

Click to expand or contract

Contact details


Show all stories by this author


Global-challenges-Data, Artificial-intelligence, Big-data
See more tags