Mitigating Query-based Neural Network Fingerprinting via Data Augmentation
نویسندگان
چکیده
Protecting the intellectual property (IP) of deep neural network (DNN) models becomes essential and urgent with rapidly increasing cost DNN training. Fingerprinting is one promising IP protection method that queries suspicious specific fingerprint samples to infer verify by comparing predictions pre-defined labels. Based on utilizing unique features target models, various fingerprinting methods are proposed effectively remotely a meager false-positive ratio. In this paper, we propose novel attack mitigate query-based based data augmentation methods. We randomized transformation input significantly mislead samples’ prediction compromise verification. Then, our can keep model utility an acceptable accuracy drop in data-free scenario (i.e. without any samples) or achieve much higher precision data-limited small number same distribution). An intensive evaluation three well-known structures datasets shows five top-tier conferences.
منابع مشابه
Private Key based query on encrypted data
Nowadays, users of information systems have inclination to use a central server to decrease data transferring and maintenance costs. Since such a system is not so trustworthy, users' data usually upkeeps encrypted. However, encryption is not a nostrum for security problems and cannot guarantee the data security. In other words, there are some techniques that can endanger security of encrypted d...
متن کاملKeyword-based Query Comprehending via Multiple Optimized-Demand Augmentation
In this paper, we consider the problem of machine reading task when the questions are in the form of keywords, rather than natural language. In recent years, researchers have achieved signicant success on machine reading comprehension tasks, such as SAD and TriviaQA. ese datasets provide a natural language question sentence and a pre-selected passage, and the goal is to answer the question a...
متن کاملData Augmentation of Spectral Data for Convolutional Neural Network (CNN) Based Deep Chemometrics
D eep learning methods are used on spectroscopic data to predict drug content in tablets from near infrared (NIR) spectra. Using convolutional neural networks (CNNs), features are extracted from the spectroscopic data. Extended multiplicative scatter correction (EMSC) and a novel spectral data augmentation method are benchmarked as preprocessing steps. The learned models perform better or on pa...
متن کاملDetecting Adversarial Examples via Neural Fingerprinting
Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose NeuralFingerprinting, a simple, yet effective method to detect adversarial examples by verifying whether model behavior is consistent with a set of secret fingerprints, inspired by the use of biometric and cryptographic signatures. The benefits of our method a...
متن کاملData Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling
We investigate the use of local Gaussian modeling (LGM) based source separation to improve speech recognition accuracy. Previous studies have shown that the LGM based source separation technique has been successfully applied to the runtime speech enhancement and the speech enhancement of training data for deep neural network (DNN) based acoustic modeling. In this paper, we propose a data augmen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Transactions on Sensor Networks
سال: 2023
ISSN: ['1550-4859', '1550-4867']
DOI: https://doi.org/10.1145/3597933