Thomas Eisenbarth

Machine learning (ML) models—particularly decision trees (DTs)—are widely adopted across various domains due to their interpretability and efficiency. However, as ML models become increasingly integrated into privacy-sensitive applications, concerns about their confidentiality have grown—particularly in light of emerging threats such as model extraction and fault injection attacks. Assessing the vulnerability of DTs under such attacks is therefore important. In this work, we present BarkBeetle, a novel model extraction attack that leverages fault injection to recover internal structural information of DT models under black-box settings. BarkBeetle employs a bottom-up recovery strategy that uses targeted fault injection at specific nodes to efficiently infer feature splits and threshold values. Our proof-of-concept implementation demonstrates that BarkBeetle requires significantly fewer queries and recovers more structural information compared to prior state-of-the-art approaches, when evaluated on DTs trained with public UCI datasets. To validate its practical feasibility, we implement BarkBeetle on a Raspberry Pi RP2350 microcontroller and perform fault injections using the Faultier voltage glitching tool. As BarkBeetle targets general DT models, we also provide an in-depth discussion on its applicability to a broader range of tree-based applications, including data stream classification, DT model variants, and tree-based cryptography schemes.

The cornerstone of modern industrial infrastructures are their digital communication systems. However, such infrastructures suffer from increased cyber-attacks and reliability issues. The RILKOSAN project tackles this issue and introduces a holistic approach to resilient industrial communication systems with a strong focus on process-industry applications and Industry 4.0. We developed a resilient communication framework that covers from networks to the devices. Thus, RILKOSAN relies on four core elements: an Intelligent Machine Learning-based Intrusion Detection System (I-IDS) with an accuracy of 99.9% at an inference throughput of 1.16 million packets/second (∼ 14Gbps); intelligent recovery with resilient network failover; a zero-trust architecture with Trusted Execution Environments (TEE); and a Hardware Security Module (HSM) that offers cryptographic primitives as a root of trust for the device level. We demonstrate our approach in real-world process industry scenarios, showing improvements in system availability and attack resilience. The project has contributed to German 6G platform initiatives and to standardization efforts in industrial communication security.

Homomorphic encryption (HE) is a promising technology for confidential cloud computing, as it allows computations on encrypted data. However, HE is computationally expensive and often memory-bound on conventional computer architectures. Processing-in-Memory (PIM) is an alternative hardware architecture that integrates processing units and memory on the same chip or memory module. PIM enables higher memory bandwidth than conventional architectures and could thus be suitable for accelerating HE. We present DRAMatic, which implements operations foundational to HE on UPMEM PIM – a programmable general-purpose PIM system developed by UPMEM. DRAMatic incorporates many arithmetic optimizations, including residue number system and number-theoretic transform techniques, and can support the large parameters required for secure homomorphic evaluations. It achieves a 334 times speed-up compared to previous HE implementations on UPMEM PIM. We also evaluate DRAMatic against Microsoft SEAL, a popular open-source HE library, regarding both runtime and energy efficiency. The results show that DRAMatic significantly closes the gap between Microsoft SEAL and HE implementations on UPMEM PIM. However, we also show that DRAMatic is currently constrained by data transfer overhead and limited multiplication performance on UPMEM PIM hardware. Finally, we discuss potential hardware extensions to UPMEM PIM.