Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls
Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial machine learning in the form of back-box attacks on online classifier APIs. We start with a deep learning based exploratory (inference) attack, which aims to build a classifier that can provide similar classification results (labels) as the target classifier. To minimize the difference between the labels returned by the inferred classifier and the target classifier, we show that the deep learning based exploratory attack requires a large number of labeled training data samples. These labels can be collected by calling the online API, but usually there is some strict rate limitation on the number of allowed API calls. To mitigate the impact of limited training data, we develop an active learning approach that first builds a classifier based on a small number of API calls and uses this classifier to select samples to further collect their labels. Then, a new classifier is built using more training data samples. This updating process can be repeated multiple times. We show that this active learning approach can build an adversarial classifier with a small statistical difference from the target classifier using only a limited number of training data samples. We further consider evasion and causative (poisoning) attacks based on the inferred classifier that is built by the exploratory attack. Evasion attack determines samples that the target classifier is likely to misclassify, whereas causative attack provides erroneous training data samples to reduce the reliability of the re-trained classifier. The success of these attacks show that adversarial machine learning emerges as a feasible threat in the realistic case with limited training data.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningBIG-bench Machine LearningInference AttackSimilar Papers 제목 키워드 기반
Self-Joint Supervised Learning
Supervised learning is a fundamental framework used to train machine learning systems. A supervised learning problem is often formulated using an i.i.d. assumption that restricts model attention to a single relevant sign…
Out-of-Distribution DetectionVulnerability Disclosure through Adaptive Black-Box Adversarial Attacks on NIDS
Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical applica…
Change Point Detectionfeature selectionResilient Linear Classification: An Approach to Deal with Attacks on Training Data
Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven t…
Autonomous VehiclesClassificationenergy managementGeneral Classification+1Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
Link prediction in dynamic graphs (LPDG) has been widely applied to real-world applications such as website recommendation, traffic flow prediction, organizational studies, etc. These models are usually kept local and se…
Deep Reinforcement LearningLink PredictionTowards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly …