Selected work

Representative Papers

Neural Network Conversion of Machine Learning Pipelines

Mar 26, 2026

This work proposes a systematic method to convert non-neural machine learning pipelines—such as those based on random forests—into neural networks, enabling unified inference and joint optimization. Leveraging knowledge distillation, the approach treats the traditional model as a “teacher” that guides the training of a neural “student” network. The framework further integrates neural architecture search with a random forest–inspired hyperparameter selection strategy to optimize the student model. Notably, this is the first effort to employ an entire non-neural machine learning pipeline as the teacher in knowledge distillation, thereby extending the scope of this technique. Experimental evaluation across 100 OpenML tasks demonstrates that the student networks consistently replicate the performance of their teacher models, confirming the feasibility and effectiveness of the proposed conversion framework.

0 citationsRead paper

Memory DisOrder: Memory Re-orderings as a Timerless Side-channel

Jan 13, 2026

This work proposes a timerless cross-process side-channel attack that exploits processor memory reordering behavior to infer the activity of other processes. Through systematic fuzzing, the study reveals the sensitivity of memory reordering in mainstream CPUs and GPUs to concurrent workloads and demonstrates how this phenomenon can be transformed into a detectable signal. The authors innovatively harness memory reordering as a practical side channel, enabling both covert communication and fingerprinting of deep neural network (DNN) architectures. Experimental results show a covert channel achieving 16 bps with 95% accuracy on an Apple M3 GPU and a potential throughput approaching 30 Kbps on x86 CPUs. Furthermore, the technique successfully performs DNN architecture fingerprinting across multiple platforms.

0 citationsRead paper

Recent publications

Latest Papers

Neural Network Conversion of Machine Learning Pipelines

Mar 26, 2026

This work proposes a systematic method to convert non-neural machine learning pipelines—such as those based on random forests—into neural networks, enabling unified inference and joint optimization. Leveraging knowledge distillation, the approach treats the traditional model as a “teacher” that guides the training of a neural “student” network. The framework further integrates neural architecture search with a random forest–inspired hyperparameter selection strategy to optimize the student model. Notably, this is the first effort to employ an entire non-neural machine learning pipeline as the teacher in knowledge distillation, thereby extending the scope of this technique. Experimental evaluation across 100 OpenML tasks demonstrates that the student networks consistently replicate the performance of their teacher models, confirming the feasibility and effectiveness of the proposed conversion framework.

0 citationsRead paper

Memory DisOrder: Memory Re-orderings as a Timerless Side-channel

Jan 13, 2026

This work proposes a timerless cross-process side-channel attack that exploits processor memory reordering behavior to infer the activity of other processes. Through systematic fuzzing, the study reveals the sensitivity of memory reordering in mainstream CPUs and GPUs to concurrent workloads and demonstrates how this phenomenon can be transformed into a detectable signal. The authors innovatively harness memory reordering as a practical side channel, enabling both covert communication and fingerprinting of deep neural network (DNN) architectures. Experimental results show a covert channel achieving 16 bps with 95% accuracy on an Apple M3 GPU and a potential throughput approaching 30 Kbps on x86 CPUs. Furthermore, the technique successfully performs DNN architecture fingerprinting across multiple platforms.

0 citationsRead paper