th<\/sup> ACM Conference on Computer and Communications Security<\/a>.<\/p>\nWhy do we need query-based systems?<\/h3>\n The ability to collect and store data has greatly increased over the last decade. Despite this data being helpful in driving scientific advancements, most of it is personal, hence why its use raises serious privacy concerns. Laws such as the EU\u2019s General Data Protection Regulation aim to prevent serious data breaches regarding personal information.<\/p>\n
This means that enabling data to be used for good, while protecting our fundamental right to privacy, is a timely and crucial process for data scientists and privacy experts.<\/p>\n
QBS systems have the potential to enable privacy-preserving anonymous data analysis at scale. Curators keep control over the data, therefore meaning they can check and examine queries sent by analysts to prevent data breaches.<\/p>\n
However, this system is flawed, as illegal attackers can bypass these systems by designing queries to infer personal information. They gain specific people\u2019s information by exploiting vulnerabilities or implementation bugs in the system, resulting in serious data breaches.<\/p>\n
Testing QuerySnout<\/h3>\n The risks of unknown strong \u2018zero-day\u2019 attacks, where hackers capitalise on system flaws, have stalled and delayed the development of QBS systems. To test the strength of these systems, data breach attacks can be simulated in order to detect information leakages and identify possible flaws.<\/p>\n
However, manually designing and implementing these attacks against complex QBS is a difficult and lengthy process. Therefore, according to the researchers, limiting the potential for security attacks is essential to enable QBS to be used safely.<\/p>\n
QuerySnout works by learning which questions to ask the system in order to gain answers. It then learns to combine the answers automatically to detect potential privacy vulnerabilities.<\/p>\n
By using Machine Learning, the model can create a data breach consisting of a collection of queries. These queries combine answers to reveal pieces of private information using a fully-automated technique called \u2018evolutionary search\u2019, enabling the model to discover the right set of questions to ask.<\/p>\n
Because the process takes place in a \u2018black box setting\u2019, the AI only needs to access the system rather than know how it works in order to detect potential data breaches.<\/p>\n
Ana-Maria Cretu, co-first author of the study, said: \u201cWe demonstrate that QuerySnout finds more powerful attacks than those currently known on real-world systems. This means our AI model is better than humans at finding these attacks.”<\/p>\n
Further developing QuerySnout to discover more advanced data breaches<\/h3>\n Presently, the QuerySnout system only tests a small number of potential data breaches. Therefore, the team is seeking to advance the system further to detect even more complicated vulnerabilities.<\/p>\n
According to Dr de Montjoye: \u201cThe main challenge moving forward will be to scale the search to a much larger number of functionalities to make sure it discovers even the most advanced attacks.\u201d<\/p>\n
Despite this, the model can enable analysts to test the robustness of QBS against different types of attackers. The development of QuerySnout represents a key step forward in securing individual privacy in relation to query-based systems.<\/p>\n","protected":false},"excerpt":{"rendered":"
Experts have devised a new AI model that can mimic and detect data breaches to preserve security and advance the use of query-based systems.<\/p>\n","protected":false},"author":22,"featured_media":27116,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[830],"tags":[570],"acf":[],"yoast_head":"\n
Data breaches can be prevented by new AI model<\/title>\n \n \n \n \n \n \n \n \n \n \n \n \n\t \n\t \n\t \n \n \n \n \n \n\t \n\t \n\t \n