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

Hiding My Real Self! Protecting Intellectual Property in Additive...

Sizhuang Liang (Georgia Institute of Technology), Saman Zonouz (Rutgers University), Raheem Beyah (Georgia Institute of Technology)

Read More

Interpretable Federated Transformer Log Learning for Cloud Threat Forensics

Gonzalo De La Torre Parra (University of the Incarnate Word, TX, USA), Luis Selvera (Secure AI and Autonomy Lab, The University of Texas at San Antonio, TX, USA), Joseph Khoury (The Cyber Center For Security and Analytics, University of Texas at San Antonio, TX, USA), Hector Irizarry (Raytheon, USA), Elias Bou-Harb (The Cyber Center For…

Read More

FitM: Binary-Only Coverage-GuidedFuzzing for Stateful Network Protocols

Dominik Maier, Otto Bittner, Marc Munier, Julian Beier (TU Berlin)

Read More

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