Brechelmacher, O., Ničković, D., Nießen, T., Sallinger, S. S., & Weissenbacher, G. (2024). Differential Property Monitoring for Backdoor Detection. In K. Ogata, D. Mery, M. Sun, & S. Liu (Eds.), Formal Methods and Software Engineering (pp. 216–236). Springer. https://doi.org/10.34726/8400
International Conference on Formal Engineering Methods 2024
en
Event date:
2-Dec-2024 - 6-Dec-2024
-
Event place:
Hiroshima, Japan
-
Number of Pages:
21
-
Publisher:
Springer
-
Peer reviewed:
Yes
-
Keywords:
Backdoors; Security; Monitoring
en
Abstract:
A faithful characterization of backdoors is a prerequisite for an effective automated detection. Unfortunately, as we demonstrate, formalization attempts in terms of temporal safety properties prove far from trivial and may involve several revisions. Moreover, given the complexity of the task at hand, a hapless revision of a property may not only eliminate but also introduce inaccuracies in the specification. We introduce a method called differential property monitoring that addresses this challenge by monitoring discrepancies between two versions of a property, and illustrate that this technique can also be used to analyze observations of untrusted components. We demonstrate the utility of the approach using a range of case studies – including the recently discovered xz backdoor.
en
Project title:
Logics for Computer Science Program at TU Wien: 101034440 (European Commission) Automated Reasoning with Theories and Induction for Software Technologies: ERC Consolidator Grant 2020 (European Commission)
