The rapid digital transformation without security considerations has resulted in the rise of global-scale cyberattacks. The first line of defense against these attacks are Network Intrusion Detection Systems (NIDS). Once deployed, however, these systems work as blackboxes with a high rate of false positives with no measurable effectiveness. There is a need to continuously test and improve these systems by emulating real-world network attack mutations. We present SynGAN, a framework that generates adversarial network attacks using the Generative Adversial Networks (GAN). SynGAN generates malicious packet flow mutations using real attack traffic, which can improve NIDS attack detection rates. As a first step, we compare two public datasets, NSL-KDD and CICIDS2017, for generating synthetic Distributed Denial of Service (DDoS) network attacks. We evaluate the attack quality (real vs. synthetic) using a gradient boosting classifier.
Xi’an Jiaotong University（西安交通大学）；CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
While machine learning (ML) has made tremendous progress during the past decade, recent research has shown that ML models are vulnerable to various security and privacy attacks. So far, most of the attacks in this field focus on discriminative models, represented by classifiers. Meanwhile, little attention has been paid to the security and privacy risks of generative models, such as generative adversarial networks (GANs). In this paper, we propose the first set of training dataset property inference attacks against GANs. Concretely, the adversary aims to infer the macro-level training dataset …
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such synthetic data can be used for a variety of downstream tasks such as training classifiers that would otherwise require the original dataset to be shared. However, recent work has shown that the GAN models and their synthetically generated data can be used to infer the training set membership by an adversary who has access to the entire dataset and some auxiliary information. Current approaches to mitigate this problem…
Stony Brook University（石溪大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Specifically, membership attack aims to check whether a given instance x was used in the training data or not. A co-membership attack checks whether the given bundle of n instances were in the training, with the prior knowledge that the bundle was either entirely used in the training or none at all. Successful membership attacks can compromise the privacy of training data when the generative mod…
Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success, model extraction attacks against generative models are less well explored. In this paper, we systematically study the feasibility of model extraction attacks against generative adversarial networks (GANs). Specifically, we first define accuracy and fidelity on model extraction attacks against GANs. Then we study model extraction attacks against GANs from the perspective of accuracy extraction and fidelity extraction…
CISPA Helmholtz Center for Information Security（亥姆霍兹信息安全研究中心）；Cyber-Defence Campus, armasuisse Science and Technology（瑞士联邦国防、民防和体育部科技局网络防御园区）
The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption has fostered the study of security and privacy risks stemming from these models. However, previous works have mainly focused on membership inference attacks. In this work, we explore one of the most severe attacks against machine learning models, namely the backdoor attack, against both autoencoders and GANs. The backdoor attack is a training time attack where the adversary imp…
Preserving Privacy in GANs Against Membership Inference Attack
École de technologie supérieure（高等技术学院）；Universidad de Buenos Aires（布宜诺斯艾利斯大学）；McGill University（麦吉尔大学）；ILLS - International Laboratory on Learning Systems（国际学习系统实验室）；MILA - Quebec AI Institute（魁北克人工智能研究所）；CNRS（法国国家科学研究中心）；CentraleSupélec（巴黎中央理工-高等电力学院）
J.P. Morgan AI Research（摩根大通人工智能研究院）；Index Exchange（Index Exchange（索引交易所））
Deep generative models, such as Generative Adversarial Networks (GANs), synthesize diverse high-fidelity data samples by estimating the underlying distribution of high dimensional data. Despite their success, GANs may disclose private information from the data they are trained on, making them susceptible to adversarial attacks such as membership inference attacks, in which an adversary aims to determine if a record was part of the training set. We propose an information theoretically motivated regularization term that prevents the generative model from overfitting to training data and encourag…
Robustness of deep learning models is a property that has recently gained increasing attention. We explore a notion of robustness for generative adversarial models that is pertinent to their internal interactive structure, and show that, perhaps surprisingly, the GAN in its original form is not robust. Our notion of robustness relies on a perturbed discriminator, or noisy, adversarial interference with its feedback. We explore, theoretically and empirically, the effect of model and training properties on this robustness. In particular, we show theoretical conditions for robustness that are sup…
TU Delft（代尔夫特理工大学）；ABB Research Switzerland（ABB瑞士研究院）
Tabular generative adversarial networks (TGAN) have recently emerged to cater to the need of synthesizing tabular data -- the most widely used data format. While synthetic tabular data offers the advantage of complying with privacy regulations, there still exists a risk of privacy leakage via inference attacks due to interpolating the properties of real data during training. Differential private (DP) training algorithms provide theoretical guarantees for training machine learning models by injecting statistical noise to prevent privacy leaks. However, the challenges of applying DP on TGAN are …
University of New South Wales（新南威尔士大学）；The Australian National University（澳大利亚国立大学）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织Data61研究所）
Generative AI (e.g., Generative Adversarial Networks - GANs) has become increasingly popular in recent years. However, Generative AI introduces significant concerns regarding the protection of Intellectual Property Rights (IPR) (resp. model accountability) pertaining to images (resp. toxic images) and models (resp. poisoned models) generated. In this paper, we propose an evaluation framework to provide a comprehensive overview of the current state of the copyright protection measures for GANs, evaluate their performance across a diverse range of GAN architectures, and identify the factors that…
Recreating cyber-attack alert data with a high level of fidelity is challenging due to the intricate interaction between features, non-homogeneity of alerts, and potential for rare yet critical samples. Generative Adversarial Networks (GANs) have been shown to effectively learn complex data distributions with the intent of creating increasingly realistic data. This paper presents the application of GANs to cyber-attack alert data and shows that GANs not only successfully learn to generate realistic alerts, but also reveal feature dependencies within alerts. This is accomplished by reviewing th…
The Australian National University（澳大利亚国立大学）；Data61
Robustness to adversarial attacks is an important concern due to the fragility of deep neural networks to small perturbations and has received an abundance of attention in recent years. Distributionally Robust Optimization (DRO), a particularly promising way of addressing this challenge, studies robustness via divergence-based uncertainty sets and has provided valuable insights into robustification strategies such as regularization. In the context of machine learning, the majority of existing results have chosen $f$-divergences, Wasserstein distances and more recently, the Maximum Mean Discrep…
Technical University of Darmstadt（达姆施塔特工业大学）；Universität der Bundeswehr München（慕尼黑联邦国防军大学）；Centre for Cognitive Science, TU Darmstadt（达姆施塔特工业大学认知科学中心）；Hessian Center for AI (hessian.AI)（黑森人工智能中心（hessian.AI））
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research has developed generative MIAs that use generative adversarial networks (GANs) as image priors tailored to a specific target model. This makes the attacks time- and resource-consuming, inflexible, and susceptible to distributional shifts between datasets. To overcome these drawbacks, we present Plug & Play Attacks, which relax the dependency between the target model and image prio…
We present two information leakage attacks that outperform previous work on membership inference against generative models. The first attack allows membership inference without assumptions on the type of the generative model. Contrary to previous evaluation metrics for generative models, like Kernel Density Estimation, it only considers samples of the model which are close to training data records. The second attack specifically targets Variational Autoencoders, achieving high membership inference accuracy. Furthermore, previous work mostly considers membership inference adversaries who perfor…
Tabular data synthesis has received wide attention in the literature. This is because available data is often limited, incomplete, or cannot be obtained easily, and data privacy is becoming increasingly important. In this work, we present a generalized GAN framework for tabular synthesis, which combines the adversarial training of GANs and the negative log-density regularization of invertible neural networks. The proposed framework can be used for two distinctive objectives. First, we can further improve the synthesis quality, by decreasing the negative log-density of real records in the proce…
The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks
Radboud University（拉德堡德大学）；Rabobank（拉德堡德银行）；Delft University of Technology（代尔夫特理工大学）；National Technical University of Athens（希腊国家技术大学）；University of Zagreb（扎格列布大学）；University of Bergen（卑尔根大学）
While data sharing is crucial for knowledge development, privacy concerns and strict regulation (e.g., European General Data Protection Regulation (GDPR)) unfortunately limits its full effectiveness. Synthetic tabular data emerges as an alternative to enable data sharing while fulfilling regulatory and privacy constraints. The state-of-the-art tabular data synthesizers draw methodologies from Generative Adversarial Networks (GAN). In this thesis, we develop CTAB-GAN, a novel conditional table GAN architecture that can effectively model diverse data types with complex distributions. CTAB-GAN is…
In this paper we investigate the ability of generative adversarial networks (GANs) to synthesize spoofing attacks on modern speaker recognition systems. We first show that samples generated with SampleRNN and WaveNet are unable to fool a CNN-based speaker recognition system. We propose a modification of the Wasserstein GAN objective function to make use of data that is real but not from the class being learned. Our semi-supervised learning method is able to perform both targeted and untargeted attacks, raising questions related to security in speaker authentication systems.
Dublin City University（都柏林城市大学）；Insight Centre for Data Analytics（Insight数据分析中心）
Access to medical data is highly restricted due to its sensitive nature, preventing communities from using this data for research or clinical training. Common methods of de-identification implemented to enable the sharing of data are sometimes inadequate to protect the individuals contained in the data. For our research, we investigate the ability of generative adversarial networks (GANs) to produce realistic medical time series data which can be used without concerns over privacy. The aim is to generate synthetic ECG signals representative of normal ECG waveforms. GANs have been used successf…
Fudan University（复旦大学）；University of California at Berkeley（加州大学伯克利分校）；Tsinghua University（清华大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually contain privacy-sensitive information. Thus far, successful model-inversion attacks have only been demonstrated on simple models, such as linear regression and logistic regression. Previous attempts to invert neural networks, even the ones with simple architectures, have failed to produce convincing results. We present a novel attack method, termed the generativ…
This work evaluates the robustness of quality measures of generative models such as Inception Score (IS) and Fréchet Inception Distance (FID). Analogous to the vulnerability of deep models against a variety of adversarial attacks, we show that such metrics can also be manipulated by additive pixel perturbations. Our experiments indicate that one can generate a distribution of images with very high scores but low perceptual quality. Conversely, one can optimize for small imperceptible perturbations that, when added to real world images, deteriorate their scores. We further extend our evaluation…
Latent-factor models (LFM) based on collaborative filtering (CF), such as matrix factorization (MF) and deep CF methods, are widely used in modern recommender systems (RS) due to their excellent performance and recommendation accuracy. However, success has been accompanied with a major new arising challenge: many applications of machine learning (ML) are adversarial in nature. In recent years, it has been shown that these methods are vulnerable to adversarial examples, i.e., subtle but non-random perturbations designed to force recommendation models to produce erroneous outputs. The goal of th…
University of Maryland（马里兰大学）；Butterfly Network（蝴蝶网络公司）
Inferring the latent variable generating a given test sample is a challenging problem in Generative Adversarial Networks (GANs). In this paper, we propose InvGAN - a novel framework for solving the inference problem in GANs, which involves training an encoder network capable of inverting a pre-trained generator network without access to any training data. Under mild assumptions, we theoretically show that using InvGAN, we can approximately invert the generations of any latent code of a trained GAN model. Furthermore, we empirically demonstrate the superiority of our inference scheme by quantit…
Over the last two decades, a lot of work has been done in improving network security, particularly in intrusion detection systems (IDS) and anomaly detection. Machine learning solutions have also been employed in IDSs to detect known and plausible attacks in incoming traffic. Parameters such as packet contents, sender IP and sender port, connection duration, etc. have been previously used to train these machine learning models to learn to differentiate genuine traffic from malicious ones. Generative Adversarial Networks (GANs) have been significantly successful in detecting such anomalies, mos…
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）
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 their models frequently with newly-collected data in an online learning scenario. In consequence, if an ML model is queried with the same set of data samples at two different points in time, it will provide different results. In this paper, we investigate whether the change in the output of a black-box ML model before and after being updated can leak informa…
Classifiers and generators have long been separated. We break down this separation and showcase that conventional neural network classifiers can generate high-quality images of a large number of categories, being comparable to the state-of-the-art generative models (e.g., DDPMs and GANs). We achieve this by computing the partial derivative of the classification loss function with respect to the input to optimize the input to produce an image. Since it is widely known that directly optimizing the inputs is similar to targeted adversarial attacks incapable of generating human-meaningful images, …
Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator's capacity to learn statistical differences in distributions. We p…
Malware authors have always been at an advantage of being able to adversarially test and augment their malicious code, before deploying the payload, using anti-malware products at their disposal. The anti-malware developers and threat experts, on the other hand, do not have such a privilege of tuning anti-malware products against zero-day attacks pro-actively. This allows the malware authors to being a step ahead of the anti-malware products, fundamentally biasing the cat and mouse game played by the two parties. In this paper, we propose a way that would enable machine learning based threat p…
Universidad Politécnica de Madrid（马德里理工大学）；Universidad Complutense de Madrid（马德里康普顿斯大学）；Instituto de Ciencias Matemáticas (CSIC-UAM-UCM-UC3M)（数学科学研究所（西班牙国家研究委员会-马德里自治大学-马德里康普顿斯大学-卡洛斯三世大学））；Telefónica I+D（西班牙电信研发公司）
Due to the growing rise of cyber attacks in the Internet, flow-based data sets are crucial to increase the performance of the Machine Learning (ML) components that run in network-based intrusion detection systems (IDS). To overcome the existing network traffic data shortage in attack analysis, recent works propose Generative Adversarial Networks (GANs) for synthetic flow-based network traffic generation. Data privacy is appearing more and more as a strong requirement when processing such network data, which suggests to find solutions where synthetic data can fully replace real data. Because of…
The privacy implications of generative adversarial networks (GANs) are a topic of great interest, leading to several recent algorithms for training GANs with privacy guarantees. By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees. First, we show that if a GAN is trained on m samples and used to generate n samples, the generated samples are (epsilon, delta)-differentially-private for (epsilon, delta) pairs where delta scales as O(n/m). We show that under some special condit…
An Intrusion Detection System (IDS) is a key cybersecurity tool for network administrators as it identifies malicious traffic and cyberattacks. With the recent successes of machine learning techniques such as deep learning, more and more IDS are now using machine learning algorithms to detect attacks faster. However, these systems lack robustness when facing previously unseen types of attacks. With the increasing number of new attacks, especially against Internet of Things devices, having a robust IDS able to spot unusual and new attacks becomes necessary. This work explores the possibility of…
University of Electronic Science Technology of China（电子科技大学）；Shanghai Jiao Tong University（上海交通大学）
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 adversarial examples and their attack success rates heavily rely on the transferability of adversarial examples. Current score-based and decision-based attacks require lots of queries for the attacked models. In this study, we propose a novel adversarial imitation attack. First, it produces a replica of the attacked model by a two-player game like the generative a…
Mobility datasets are fundamental for evaluating algorithms pertaining to geographic information systems and facilitating experimental reproducibility. But privacy implications restrict sharing such datasets, as even aggregated location-data is vulnerable to membership inference attacks. Current synthetic mobility dataset generators attempt to superficially match a priori modeled mobility characteristics which do not accurately reflect the real-world characteristics. Modeling human mobility to generate synthetic yet semantically and statistically realistic trajectories is therefore crucial for…
Domain Generation Algorithms (DGAs) are frequently used to generate numerous domains for use by botnets. These domains are often utilized as rendezvous points for servers that malware has command and control over. There are many algorithms that are used to generate domains, however many of these algorithms are simplistic and easily detected by traditional machine learning techniques. In this paper, three variants of Generative Adversarial Networks (GANs) are optimized to generate domains which have similar characteristics of benign domains, resulting in domains which greatly evade several stat…
Recommender systems are an essential part of any e-commerce platform. Recommendations are typically generated by aggregating large amounts of user data. A malicious actor may be motivated to sway the output of such recommender systems by injecting malicious datapoints to leverage the system for financial gain. In this work, we propose a semi-supervised attack detection algorithm to identify the malicious datapoints. We do this by leveraging a portion of the dataset that has a lower chance of being polluted to learn the distribution of genuine datapoints. Our proposed approach modifies the Gene…
Alibaba Group（阿里巴巴集团）；Huazhong University of Science and Technology（华中科技大学）；Xi’an International Studies University（西安外国语大学）
The behavior of malware threats is gradually increasing, heightened the need for malware detection. However, existing malware detection methods only target at the existing malicious samples, the detection of fresh malicious code and variants of malicious code is limited. In this paper, we propose a novel scheme that detects malware and its variants efficiently. Based on the idea of the generative adversarial networks (GANs), we obtain the `true' sample distribution that satisfies the characteristics of the real malware, use them to deceive the discriminator, thus achieve the defense against ma…
The proliferation of smart, connected, always listening devices have introduced significant privacy risks to users in a smart home environment. Beyond the notable risk of eavesdropping, intruders can adopt machine learning techniques to infer sensitive information from audio recordings on these devices, resulting in a new dimension of privacy concerns and attack variables to smart home users. Techniques such as sound masking and microphone jamming have been effectively used to prevent eavesdroppers from listening in to private conversations. In this study, we explore the problem of adversaries…
Deep Neural Networks (DNNs) have been shown vulnerable to Test-Time Evasion attacks (TTEs, or adversarial examples), which, by making small changes to the input, alter the DNN's decision. We propose an unsupervised attack detector on DNN classifiers based on class-conditional Generative Adversarial Networks (GANs). We model the distribution of clean data conditioned on the predicted class label by an Auxiliary Classifier GAN (AC-GAN). Given a test sample and its predicted class, three detection statistics are calculated based on the AC-GAN Generator and Discriminator. Experiments on image clas…
National Taiwan University（台湾大学）；Academia Sinica（中央研究院）；National Yang Ming Chiao Tung University（国立阳明交通大学）
With the successful creation of high-quality image-to-image (Img2Img) translation GANs comes the non-ethical applications of DeepFake and DeepNude. Such misuses of img2img techniques present a challenging problem for society. In this work, we tackle the problem by introducing the Limit-Aware Self-Guiding Gradient Sliding Attack (LaS-GSA). LaS-GSA follows the Nullifying Attack to cancel the img2img translation process under a black-box setting. In other words, by processing input images with the proposed LaS-GSA before publishing, any targeted img2img GANs can be nullified, preventing the model…
Nanyang Technological University（南洋理工大学）；Alibaba Group（阿里巴巴集团）；Kyushu University（九州大学）；East China Normal University（华东师范大学）；Zhejiang University（浙江大学）
In recent years, generative adversarial networks (GANs) and its variants have achieved unprecedented success in image synthesis. They are widely adopted in synthesizing facial images which brings potential security concerns to humans as the fakes spread and fuel the misinformation. However, robust detectors of these AI-synthesized fake faces are still in their infancy and are not ready to fully tackle this emerging challenge. In this work, we propose a novel approach, named FakeSpotter, based on monitoring neuron behaviors to spot AI-synthesized fake faces. The studies on neuron coverage and i…
Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex, high-dimensional manifolds. However, even with their increasing industrial adoption, they haven't been subject to rigorous security and privacy analysis. In this work we examine one such aspect, namely backdoor attacks on DGMs which can significantly limit the applicability of pre-trained models within a model supply chain and at the very least cause massive reputation damage for companies outsourcing DGMs form third parties. While simila…
United Nations University（联合国大学）；The University of Tokyo（东京大学）
An attack on deep learning systems where intelligent machines collaborate to solve problems could cause a node in the network to make a mistake on a critical judgment. At the same time, the security and privacy concerns of AI have galvanized the attention of experts from multiple disciplines. In this research, we successfully mounted adversarial attacks on a federated learning (FL) environment using three different datasets. The attacks leveraged generative adversarial networks (GANs) to affect the learning process and strive to reconstruct the private data of users by learning hidden features…
Aalto University（阿尔托大学）；University of Waterloo（滑铁卢大学）；University of Helsinki（赫尔辛基大学）
Machine learning models are typically made available to potential client users via inference APIs. Model extraction attacks occur when a malicious client uses information gleaned from queries to the inference API of a victim model $F_V$ to build a surrogate model $F_A$ with comparable functionality. Recent research has shown successful model extraction of image classification, and natural language processing models. In this paper, we show the first model extraction attack against real-world generative adversarial network (GAN) image translation models. We present a framework for conducting suc…
