Ahmed Salem (CISPA Helmholtz Center for Information Security), Michael Backes (CISPA Helmholtz Center for Information Security), Yang Zhang (CISPA Helmholtz Center for Information Security)

Machine learning (ML) has established itself as a cornerstone for various critical applications ranging from autonomous driving to authentication systems. However, with this increasing adoption rate of machine learning models, multiple attacks have emerged. One class of such attacks is training time attack, whereby an adversary executes their attack before or during the machine learning model training. In this work, we propose a new training time attack against computer vision based machine learning models, namely model hijacking attack. The adversary aims to hijack a target model to execute a different task than its original one without the model owner noticing. Model hijacking can cause accountability and security risks since a hijacked model owner can be framed for having their model offering illegal or unethical services. Model hijacking attacks are launched in the same way as existing data poisoning attacks. However, one requirement of the model hijacking attack is to be stealthy, i.e., the data samples used to hijack the target model should look similar to the model's original training dataset. To this end, we propose two different model hijacking attacks, namely Chameleon and Adverse Chameleon, based on a novel encoder-decoder style ML model, namely the Camouflager. Our evaluation shows that both of our model hijacking attacks achieve a high attack success rate, with a negligible drop in model utility.

View More Papers

Property Inference Attacks Against GANs

Junhao Zhou (Xi'an Jiaotong University), Yufei Chen (Xi'an Jiaotong University), Chao Shen (Xi'an Jiaotong University), Yang Zhang (CISPA Helmholtz Center for Information Security)

Read More

Chosen-Instruction Attack Against Commercial Code Virtualization Obfuscators

Shijia Li (College of Computer Science, NanKai University and the Tianjin Key Laboratory of Network and Data Security Technology), Chunfu Jia (College of Computer Science, NanKai University and the Tianjin Key Laboratory of Network and Data Security Technology), Pengda Qiu (College of Computer Science, NanKai University and the Tianjin Key Laboratory of Network and Data…

Read More

F-PKI: Enabling Innovation and Trust Flexibility in the HTTPS...

Laurent Chuat (ETH Zurich), Cyrill Krähenbühl (ETH Zürich), Prateek Mittal (Princeton University), Adrian Perrig (ETH Zurich)

Read More