Uploaded September 2026 | Updated November 2026, 5 days ago
WIP: On the Real-World Applicability of Automotive CAN Intrusion Detection Systems
Kristijan Lazeski, Darmstadt University of Applied Sciences and European University of Technology; Michael Zohner, University of Applied Sciences Fulda; Jannis Hamborg, Darmstadt University of Applied Sciences and European University of Technology; Christoph Krauß and Alexander Wiesmaier, Darmstadt University of Applied Sciences, European University of Technology, and National Research Center for Applied Cybersecurity ATHENE
Machine Learning (ML)-based Controller Area Network (CAN) Intrusion Detection Systems (IDS) are widely studied and used to detect and mitigate attacks on in-vehicle communication. Despite frequent reports on high detection performance for well-established datasets, the practical applicability and robustness against real-world attackers of the trained solutions is rarely discussed. This work presents a preliminary analysis of the practical robustness of ML-based CAN IDS solutions, with a focus on per-frame, binary intrusion detection approaches. Our approach consists of three steps: (1) We analyze common datasets used for training and evaluating ML-based CAN IDS, (2) train human-interpretable decision trees on the datasets and investigate their learned classification rules1, and (3) critically evaluate the models against a practical attacker model. We observe that many commonly used CAN IDS datasets only include simple and easily distinguishable attacks. Consequently, ML-based models trained on these datasets tend to learn dataset-specific statistical artifacts or shortcuts rather than robust or semantically meaningful detection logic, a finding we demonstrate specifically within the scope of per-frame, binary detection. While our results are preliminary and limited to this detection paradigm, they show that high detection performance is not inherently indicative of practical robustness. We therefore argue that new detection strategies founded upon vehicle specifications and domain knowledge, in combination with ML tools, may offer more transparent and reliable protection than purely ML-driven approaches, and we call for broader evaluation across more diverse detection settings in future work.
View the full VehicleSec '26 program at usenix.org/conference/vehiclesec26/program
WIP: On the Real-World Applicability of Automotive CAN Intrusion Detection Systems
Kristijan Lazeski, Darmstadt University of Applied Sciences and European University of Technology; Michael Zohner, University of Applied Sciences Fulda; Jannis Hamborg, Darmstadt University of Applied Sciences and European University of Technology; Christoph Krauß and Alexander Wiesmaier, Darmstadt University of Applied Sciences, European University of Technology, and National Research Center for Applied Cybersecurity ATHENE
Machine Learning (ML)-based Controller Area Network (CAN) Intrusion Detection Systems (IDS) are widely studied and used to detect and mitigate attacks on in-vehicle communication. Despite frequent reports on high detection performance for well-established datasets, the practical applicability and robustness against real-world attackers of the trained solutions is rarely discussed. This work presents a preliminary analysis of the practical robustness of ML-based CAN IDS solutions, with a focus on per-frame, binary intrusion detection approaches. Our approach consists of three steps: (1) We analyze common datasets used for training and evaluating ML-based CAN IDS, (2) train human-interpretable decision trees on the datasets and investigate their learned classification rules1, and (3) critically evaluate the models against a practical attacker model. We observe that many commonly used CAN IDS datasets only include simple and easily distinguishable attacks. Consequently, ML-based models trained on these datasets tend to learn dataset-specific statistical artifacts or shortcuts rather than robust or semantically meaningful detection logic, a finding we demonstrate specifically within the scope of per-frame, binary detection. While our results are preliminary and limited to this detection paradigm, they show that high detection performance is not inherently indicative of practical robustness. We therefore argue that new detection strategies founded upon vehicle specifications and domain knowledge, in combination with ML tools, may offer more transparent and reliable protection than purely ML-driven approaches, and we call for broader evaluation across more diverse detection settings in future work.
View the full VehicleSec '26 program at usenix.org/conference/vehiclesec26/program




![USENIX Security 26 - PICS: Private Intersection over Committed (and reusable) Sets
USENIX Security 26 - PICS: Private Intersection over Committed (and reusable) Sets
Aarushi Goel, Rutgers University; Peihan Miao and Phuoc Van Long Pham, Brown University; Satvinder Singh, Purdue University
Private Set Intersection (PSI) enables two parties to compute the intersection of their private sets without revealing any additional information. While maliciously secure PSI protocols prevent many attacks, adversaries can still exploit them by using inconsistent inputs across multiple sessions. This limitation stems from the definition of malicious security in secure multiparty computation, but is particularly problematic in PSI because: (1) real-world applications—such as Apples PSI protocol for CSAM detection and private contact discovery in messaging apps—often require multiple PSI executions over consistent inputs, and (2) the PSI functionality makes it relatively easy for adversaries to infer additional information.
We propose Private Intersection over Committed Sets (PICS), a new framework that enforces input consistency across multiple sessions via committed sets. Building on the state-of-the-art maliciously secure PSI framework (i.e., VOLE-PSI [EUROCRYPT 2021]), we present an efficient instantiation of PICS using lightweight cryptographic tools. Our protocol achieves strong receiver-side input consistency (i.e., the receiver uses the exact committed set) and weak sender-side input consistency (i.e., the sender cannot inject new elements into the committed set but can potentially use a subset of the committed set). We implement our protocol to demonstrate concrete efficiency. Compared to VOLE-PSI, our communication overhead is a small constant between 1.57 - 2.04× for set sizes between 216-224, and the total end-to-end running time overhead is 1.22 - 1.98× across various network settings.
View the full USENIX Security 26 program at https://www.usenix.org/conference/usenixsecurity26/technical-sessions USENIX Security 26 - PICS: Private Intersection over Committed (and reusable) Sets](https://i.ytimg.com/vi/Q6rhdJr_J4M/mqdefault.jpg)





