Rui Wen (CISPA Helmholtz Center for Information Security), Michael Backes (CISPA Helmholtz Center for Information Security), Yang Zhang (CISPA Helmholtz Center for Information Security)

Machine learning has revolutionized numerous domains, playing a crucial role in driving advancements and enabling data-centric processes. The significance of data in training models and shaping their performance cannot be overstated. Recent research has highlighted the heterogeneous impact of individual data samples, particularly the presence of valuable data that significantly contributes to the utility and effectiveness of machine learning models. However, a critical question remains unanswered: are these valuable data samples more vulnerable to machine learning attacks? In this work, we investigate the relationship between data importance and machine learning attacks by analyzing five distinct attack types. Our findings reveal notable insights. For example, we observe that high importance data samples exhibit increased vulnerability in certain attacks, such as membership inference and model stealing. These findings also carry practical implications, inspiring researchers to design more efficient attacks. By analyzing the linkage between membership inference vulnerability and data importance, we demonstrate that sample characteristics can be integrated into membership metrics by introducing sample-specific criteria, therefore enhancing the membership inference performance. These findings emphasize the urgent need for innovative defense mechanisms that strike a balance between maximizing utility and safeguarding valuable data against potential exploitation.

View More Papers

“I’m 73, you can’t expect me to have multiple...

Ashley Sheil (Munster Technological University), Jacob Camilleri (Munster Technological University), Michelle O Keeffe (Munster Technological University), Melanie Gruben (Munster Technological University), Moya Cronin (Munster Technological University) and Hazel Murray (Munster Technological University)

Read More

Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing

Ruyi Ding (Northeastern University), Tong Zhou (Northeastern University), Lili Su (Northeastern University), Aidong Adam Ding (Northeastern University), Xiaolin Xu (Northeastern University), Yunsi Fei (Northeastern University)

Read More

Can Public IP Blocklists Explain Internet Radiation?

Simone Cossaro (University of Trieste), Damiano Ravalico (University of Trieste), Rodolfo Vieira Valentim (University of Turin), Martino Trevisan (University of Trieste), Idilio Drago (University of Turin)

Read More

Privacy-Enhancing Technologies Against Physical-Layer and Link-Layer Device Tracking: Trends,...

Apolline Zehner (Universite libre de Bruxelles), Iness Ben Guirat (Universite libre de Bruxelles), Jan Tobias Muhlberg (Universite libre de Bruxelles)

Read More