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

PHYjacking: Physical Input Hijacking for Zero-Permission Authorization Attacks on...

Xianbo Wang (The Chinese University of Hong Kong), Shangcheng Shi (The Chinese University of Hong Kong), Yikang Chen (The Chinese...

Read More

Drivers and Passengers Maybe the Weakest Link in the...

Aiping Xiong (Pennsylvania State University), Zekun Cai (Pennsylvania State University) and Tianhao Wang (University of Virginia)

Read More

Fighting Fake News in Encrypted Messaging with the Fuzzy...

Linsheng Liu (George Washington University), Daniel S. Roche (United States Naval Academy), Austin Theriault (George Washington University), Arkady Yerukhimovich (George...

Read More

SoK: A Proposal for Incorporating Gamified Cybersecurity Awareness in...

June De La Cruz (INSPIRIT Lab, University of Denver), Sanchari Das (INSPIRIT Lab, University of Denver)

Read More