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

Probe the Proto: Measuring Client-Side Prototype Pollution Vulnerabilities of...

Zifeng Kang (Johns Hopkins University), Song Li (Johns Hopkins University), Yinzhi Cao (Johns Hopkins University)

Read More

Hazard Integrated: Understanding Security Risks in App Extensions to...

Mingming Zha (Indiana University Bloomington), Jice Wang (National Computer Network Intrusion Protection Center, University of Chinese Academy of Sciences), Yuhong Nan (Sun Yat-sen University), Xiaofeng Wang (Indiana Unversity Bloomington), Yuqing Zhang (National Computer Network Intrusion Protection Center, University of Chinese Academy of Sciences), Zelin Yang (National Computer Network Intrusion Protection Center, University of Chinese Academy…

Read More

Semantic-Informed Driver Fuzzing Without Both the Hardware Devices and...

Wenjia Zhao (Xi'an Jiaotong University and University of Minnesota), Kangjie Lu (University of Minnesota), Qiushi Wu (University of Minnesota), Yong Qi (Xi'an Jiaotong University)

Read More

Demo: A Simulator for Cooperative and Automated Driving Security

Mohammed Lamine Bouchouia (Telecom Paris - Institut Polytechnique de Paris), Jean-Philippe Monteuuis (Qualcomm), Houda Labiod (Telecom Paris - Institut Polytechnique de Paris), Ons Jelassi, Wafa Ben Jaballah (Thales) and Jonathan Petit (Telecom Paris - Institut Polytechnique de Paris)

Read More