NDSS 2024 - Transpose Attack: Stealing Datasets with Bidirectional Training

SESSION 13B-1 Transpose Attack: Stealing Datasets with Bidirectional Training
Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to hide rogue models within seemingly legitimate models. In addition, in this work we show that neural networks can be taught to systematically memorize and retrieve specific samples from datasets. Together, these findings expose a novel method in which adversaries can exfiltrate datasets from protected learning environments under the guise of legitimate models.
We focus on the data exfiltration attack and show that modern architectures can be used to secretly exfiltrate tens of thousands of samples with high fidelity, high enough to compromise data privacy and even train new models. Moreover, to mitigate this threat we propose a novel approach for detecting infected models.
PAPER
www.ndss-sympo...
AUTHORS
Guy Amit (Ben-Gurion University), Moshe Levy (Ben-Gurion University), Yisroel Mirsky (Ben-Gurion University)
Network and Distributed System Security (NDSS) Symposium 2024, 26 February - 1 March 2024 in San Diego, California.
ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.
www.ndss-sympo...
#NDSS #NDSS24 #NDSS2024 #InternetSecurity