Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries
Network weights can be reverse-engineered given enough informative samples of a network's input-output function. In a teacher-student setup, this translates into collecting a dataset of the teacher mapping -- querying the teacher -- and fitting a student to imitate such mapping. A sensible choice of queries is the dataset the teacher is trained on. But current methods fail when the teacher parameters are more numerous than the training data, because the student overfits to the queries instead of aligning its parameters to the teacher. In this work, we explore augmentation techniques to best sample the input-output mapping of a teacher network, with the goal of eliciting a rich set of representations from the teacher hidden layers. We discover that standard augmentations such as rotation, flipping, and adding noise, bring little to no improvement to the identification problem. We design new data augmentation techniques tailored to better sample the representational space of the network's hidden layers. With our augmentations we extend the state-of-the-art range of recoverable network sizes. To test their scalability, we show that we can recover networks of up to 100 times more parameters than training data-points.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
MalMixer: Few-Shot Malware Classification with Retrieval-Augmented Semi-Supervised Learning
Recent growth and proliferation of malware have tested practitioners ability to promptly classify new samples according to malware families. In contrast to labor-intensive reverse engineering efforts, machine learning ap…
Data AugmentationMalware ClassificationRetrievalVision Transformers for Efficient Indoor Pathloss Radio Map Prediction
Indoor pathloss prediction is a fundamental task in wireless network planning, yet it remains challenging due to environmental complexity and data scarcity. In this work, we propose a deep learning-based approach utilizi…
Data AugmentationFeature EngineeringSNIFF: Reverse Engineering of Neural Networks with Fault Attacks
Neural networks have been shown to be vulnerable against fault injection attacks. These attacks change the physical behavior of the device during the computation, resulting in a change of value that is currently being co…
CADENA: Stepwise CAD Reverse Engineering
Computer-Aided Design (CAD) underpins modern engineering, yet converting existing shapes into editable models still demands substantial expert effort. Most AI systems emit the entire CAD program in a single pass, never i…
Black-Box Guardrail Reverse-engineering Attack
Large language models (LLMs) increasingly employ guardrails to enforce ethical, legal, and application-specific constraints on their outputs. While effective at mitigating harmful responses, these guardrails introduce a …
Reinforcement LearningData Augmentation