VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting

Abstract

Deep learning has become popular, and numerous cloud-based services are provided to help customers develop and deploy deep learning applications. Meanwhile, various attack techniques have also been discovered to stealthily compromise the model's integrity. When a cloud customer deploys a deep learning model in the cloud and serves it to end-users, it is important for him to be able to verify that the deployed model has not been tampered with, and the model's integrity is protected. We propose a new low-cost and self-served methodology for customers to verify that the model deployed in the cloud is intact, while having only black-box access (e.g., via APIs) to the deployed model. Customers can detect arbitrary changes to their deep learning models. Specifically, we define \texttt{Sensitive-Sample} fingerprints, which are a small set of transformed inputs that make the model outputs sensitive to the model's parameters. Even small weight changes can be clearly reflected in the model outputs, and observed by the customer. Our experiments on different types of model integrity attacks show that we can detect model integrity breaches with high accuracy ($>$99\%) and low overhead ($<$10 black-box model accesses).

References in corpus (11)

• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Understanding Black-box Predictions via Influence Functions
• Compressing Deep Convolutional Networks using Vector Quantization
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Poisoning Attacks against Support Vector Machines
• Robust Physical-World Attacks on Deep Learning Models
• Is feature selection secure against training data poisoning?
• MagNet: a Two-Pronged Defense against Adversarial Examples
• Generative Poisoning Attack Method Against Neural Networks
• PoTrojan: powerful neural-level trojan designs in deep learning models

Cited by in corpus (3)

• Neural-BO: A Black-box Optimization Algorithm using Deep Neural Networks
• DiabDeep: Pervasive Diabetes Diagnosis based on Wearable Medical Sensors and Efficient Neural Networks
• VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)