相关论文: MAZE: Data-Free Model Stealing Attack Using Zeroth…

Membership inference (MI) attacks exploit the fact that machine learning algorithms sometimes leak information about their training data through the learned model. In this work, we study membership inference in the white-box setting in…

Machine learning (ML) has progressed rapidly during the past decade and the major factor that drives such development is the unprecedented large-scale data. As data generation is a continuous process, this leads to ML model owners updating…

Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies show that machine learning services face severe privacy…

Machine learning is a popular approach to signatureless malware detection because it can generalize to never-before-seen malware families and polymorphic strains. This has resulted in its practical use for either primary detection engines…

Due to the proliferation of malware, defenders are increasingly turning to automation and machine learning as part of the malware detection tool-chain. However, machine learning models are susceptible to adversarial attacks, requiring the…

Background: Machine learning techniques have been widely used and demonstrate promising performance in many software security tasks such as software vulnerability prediction. However, the class ratio within software vulnerability datasets…

To provide a foundation for the research of deep learning models, the construction of model pool is an essential step. This paper proposes a Training-Free and Efficient Model Generation and Enhancement Scheme (MGE). This scheme primarily…

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing…

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…

Model inversion attacks (MIAs) seek to infer the private training data of a target classifier by generating synthetic images that reflect the characteristics of the target class through querying the model. However, prior studies have relied…

Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible…

Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service (MLaaS) platforms by ``stealing'' the functionality of confidential machine-learning models through querying black-box APIs. Over seven years have…

Several companies often safeguard their trained deep models (i.e., details of architecture, learnt weights, training details etc.) from third-party users by exposing them only as black boxes through APIs. Moreover, they may not even provide…

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested…

Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is…

Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft. The attacker will train an own substitute model that…

Neural networks are vulnerable to adversarial examples, which are malicious inputs crafted to fool pre-trained models. Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted…

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typically require a…

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output…

Model stealing attacks pose an existential threat to Machine Learning as a Service (MLaaS), allowing adversaries to replicate proprietary models for a fraction of their training cost. While Data-Free Model Extraction (DFME) has emerged as a…