arXiv subjects

Haojin Zhu

Publications and source records attributed to Haojin Zhu.

28 records · Page 2Linked to original sources

arXiv2022

Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99 within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.

cs.CR↗

arXiv2021

Hidden Backdoors in Human-Centric Language Models

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick the model into producing unexpected behaviors. In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. We deploy our hidden backdoors through two state-of-the-art trigger embedding methods. The first approach via homograph replacement, embeds the trigger into deep neural networks through the visual spoofing of lookalike character replacement. The second approach uses subtle differences between text generated by language models and real natural text to produce trigger sentences with correct grammar and high fluency. We demonstrate that the proposed hidden backdoors can be effective across three downstream security-critical NLP tasks, representative of modern human-centric NLP systems, including toxic comment detection, neural machine translation (NMT), and question answering (QA). Our two hidden backdoor attacks can achieve an Attack Success Rate (ASR) of at least $97\%$ with an injection rate of only $3\%$ in toxic comment detection, $95.1\%$ ASR in NMT with less than $0.5\%$ injected data, and finally $91.12\%$ ASR against QA updated with only 27 poisoning data samples on a model previously trained with 92,024 samples (0.029\%). We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.

cs.CL↗

arXiv2021

Dissecting Click Fraud Autonomy in the Wild

Although the use of pay-per-click mechanisms stimulates the prosperity of the mobile advertisement network, fraudulent ad clicks result in huge financial losses for advertisers. Extensive studies identify click fraud according to click/traffic patterns based on dynamic analysis. However, in this study, we identify a novel click fraud, named humanoid attack, which can circumvent existing detection schemes by generating fraudulent clicks with similar patterns to normal clicks. We implement the first tool ClickScanner to detect humanoid attacks on Android apps based on static analysis and variational AutoEncoder (VAE) with limited knowledge of fraudulent examples. We define novel features to characterize the patterns of humanoid attacks in the apps' bytecode level. ClickScanner builds a data dependency graph (DDG) based on static analysis to extract these key features and form a feature vector. We then propose a classification model only trained on benign datasets to overcome the limited knowledge of humanoid attacks. We leverage ClickScanner to conduct the first large-scale measurement on app markets (i.e.,120,000 apps from Google Play and Huawei AppGallery) and reveal several unprecedented phenomena. First, even for the top-rated 20,000 apps, ClickScanner still identifies 157 apps as fraudulent, which shows the prevalence of humanoid attacks. Second, it is observed that the ad SDK-based attack (i.e., the fraudulent codes are in the third-party ad SDKs) is now a dominant attack approach. Third, the manner of attack is notably different across apps of various categories and popularities. Finally, we notice there are several existing variants of the humanoid attack. Additionally, our measurements demonstrate the proposed ClickScanner is accurate and time-efficient (i.e., the detection overhead is only 15.35% of those of existing schemes).

cs.CR↗

arXiv2020

Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behavior. In this paper, we create covert and scattered triggers for backdoor attacks, invisible backdoors, where triggers can fool both DNN models and human inspection. We apply our invisible backdoors through two state-of-the-art methods of embedding triggers for backdoor attacks. The first approach on Badnets embeds the trigger into DNNs through steganography. The second approach of a trojan attack uses two types of additional regularization terms to generate the triggers with irregular shape and size. We use the Attack Success Rate and Functionality to measure the performance of our attacks. We introduce two novel definitions of invisibility for human perception; one is conceptualized by the Perceptual Adversarial Similarity Score (PASS) and the other is Learned Perceptual Image Patch Similarity (LPIPS). We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators. We finally argue that the proposed invisible backdoor attacks can effectively thwart the state-of-the-art trojan backdoor detection approaches, such as Neural Cleanse and TABOR.

cs.CR↗

arXiv2018

Differentially Private Data Generative Models

Deep neural networks (DNNs) have recently been widely adopted in various applications, and such success is largely due to a combination of algorithmic breakthroughs, computation resource improvements, and access to a large amount of data. However, the large-scale data collections required for deep learning often contain sensitive information, therefore raising many privacy concerns. Prior research has shown several successful attacks in inferring sensitive training data information, such as model inversion, membership inference, and generative adversarial networks (GAN) based leakage attacks against collaborative deep learning. In this paper, to enable learning efficiency as well as to generate data with privacy guarantees and high utility, we propose a differentially private autoencoder-based generative model (DP-AuGM) and a differentially private variational autoencoder-based generative model (DP-VaeGM). We evaluate the robustness of two proposed models. We show that DP-AuGM can effectively defend against the model inversion, membership inference, and GAN-based attacks. We also show that DP-VaeGM is robust against the membership inference attack. We conjecture that the key to defend against the model inversion and GAN-based attacks is not due to differential privacy but the perturbation of training data. Finally, we demonstrate that both DP-AuGM and DP-VaeGM can be easily integrated with real-world machine learning applications, such as machine learning as a service and federated learning, which are otherwise threatened by the membership inference attack and the GAN-based attack, respectively.

cs.CR↗

arXiv2017

Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks

Popular User-Review Social Networks (URSNs)---such as Dianping, Yelp, and Amazon---are often the targets of reputation attacks in which fake reviews are posted in order to boost or diminish the ratings of listed products and services. These attacks often emanate from a collection of accounts, called Sybils, which are collectively managed by a group of real users. A new advanced scheme, which we term elite Sybil attacks, recruits organically highly-rated accounts to generate seemingly-trustworthy and realistic-looking reviews. These elite Sybil accounts taken together form a large-scale sparsely-knit Sybil network for which existing Sybil fake-review defense systems are unlikely to succeed. In this paper, we conduct the first study to define, characterize, and detect elite Sybil attacks. We show that contemporary elite Sybil attacks have a hybrid architecture, with the first tier recruiting elite Sybil workers and distributing tasks by Sybil organizers, and with the second tier posting fake reviews for profit by elite Sybil workers. We design ElsieDet, a three-stage Sybil detection scheme, which first separates out suspicious groups of users, then identifies the campaign windows, and finally identifies elite Sybil users participating in the campaigns. We perform a large-scale empirical study on ten million reviews from Dianping, by far the most popular URSN service in China. Our results show that reviews from elite Sybil users are more spread out temporally, craft more convincing reviews, and have higher filter bypass rates. We also measure the impact of Sybil campaigns on various industries (such as cinemas, hotels, restaurants) as well as chain stores, and demonstrate that monitoring elite Sybil users over time can provide valuable early alerts against Sybil campaigns.

cs.SI↗

arXiv2017

Automated Poisoning Attacks and Defenses in Malware Detection Systems: An Adversarial Machine Learning Approach

The evolution of mobile malware poses a serious threat to smartphone security. Today, sophisticated attackers can adapt by maximally sabotaging machine-learning classifiers via polluting training data, rendering most recent machine learning-based malware detection tools (such as Drebin, DroidAPIMiner, and MaMaDroid) ineffective. In this paper, we explore the feasibility of constructing crafted malware samples; examine how machine-learning classifiers can be misled under three different threat models; then conclude that injecting carefully crafted data into training data can significantly reduce detection accuracy. To tackle the problem, we propose KuafuDet, a two-phase learning enhancing approach that learns mobile malware by adversarial detection. KuafuDet includes an offline training phase that selects and extracts features from the training set, and an online detection phase that utilizes the classifier trained by the first phase. To further address the adversarial environment, these two phases are intertwined through a self-adaptive learning scheme, wherein an automated camouflage detector is introduced to filter the suspicious false negatives and feed them back into the training phase. We finally show that KuafuDet can significantly reduce false negatives and boost the detection accuracy by at least 15%. Experiments on more than 250,000 mobile applications demonstrate that KuafuDet is scalable and can be highly effective as a standalone system.

cs.CR↗

arXiv2014

HVSTO: Efficient Privacy Preserving Hybrid Storage in Cloud Data Center

In cloud data center, shared storage with good management is a main structure used for the storage of virtual machines (VM). In this paper, we proposed Hybrid VM storage (HVSTO), a privacy preserving shared storage system designed for the virtual machine storage in large-scale cloud data center. Unlike traditional shared storage, HVSTO adopts a distributed structure to preserve privacy of virtual machines, which are a threat in traditional centralized structure. To improve the performance of I/O latency in this distributed structure, we use a hybrid system to combine solid state disk and distributed storage. From the evaluation of our demonstration system, HVSTO provides a scalable and sufficient throughput for the platform as a service infrastructure.

cs.DC↗

arXiv2013

All Your Location are Belong to Us: Breaking Mobile Social Networks for Automated User Location Tracking

Many popular location-based social networks (LBSNs) support built-in location-based social discovery with hundreds of millions of users around the world. While user (near) realtime geographical information is essential to enable location-based social discovery in LBSNs, the importance of user location privacy has also been recognized by leading real-world LBSNs. To protect user's exact geographical location from being exposed, a number of location protection approaches have been adopted by the industry so that only relative location information are publicly disclosed. These techniques are assumed to be secure and are exercised on the daily base. In this paper, we question the safety of these location-obfuscation techniques used by existing LBSNs. We show, for the first time, through real world attacks that they can all be easily destroyed by an attacker with the capability of no more than a regular LBSN user. In particular, by manipulating location information fed to LBSN client app, an ill-intended regular user can easily deduce the exact location information by running LBSN apps as location oracle and performing a series of attacking strategies. We develop an automated user location tracking system and test it on the most popular LBSNs including Wechat, Skout and Momo. We demonstrate its effectiveness and efficiency via a 3 week real-world experiment with 30 volunteers. Our evaluation results show that we could geo-locate a target with high accuracy and can readily recover users' Top 5 locations. We also propose to use grid reference system and location classification to mitigate the attacks. Our work shows that the current industrial best practices on user location privacy protection are completely broken, and it is critical to address this immediate threat.

cs.SI↗

arXiv2013

YouSense: Mitigating Entropy Selfishness in Distributed Collaborative Spectrum Sensing

Collaborative spectrum sensing has been recognized as a promising approach to improve the sensing performance via exploiting the spatial diversity of the secondary users. In this study, a new selfishness issue is identified, that selfish users sense no spectrum in collaborative sensing. For easier presentation, it's denoted as entropy selfishness. This selfish behavior is difficult to distinguish, making existing detection based incentive schemes fail to work. To thwart entropy selfishness in distributed collaborative sensing, we propose YouSense, a One-Time Pad (OTP) based incentive design that could naturally isolate entropy selfish users from the honest users without selfish node detection. The basic idea of YouSense is to construct a trapdoor one-time pad for each sensing report by combining the original report and a random key. Such a one-time pad based encryption could prevent entropy selfish users from accessing the original sensing report while enabling the honest users to recover the report. Different from traditional cryptography based OTP which requires the key delivery, YouSense allows an honest user to recover the pad (or key) by exploiting a unique characteristic of collaborative sensing that different secondary users share some common observations on the same radio spectrum. We further extend YouSense to improve the recovery successful rate by reducing the cardinality of set of the possible pads. By extensive USRP based experiments, we show that YouSense can successfully thwart entropy selfishness with low system overhead.

cs.NI↗