Electric vehicles (EVs) have become one of the promising solutions to the ever-evolving environmental and energy crisis. The key to the wide adoption of EVs is a pervasive charging infrastructure, composed of both the private/home chargers and the public/commercial charging stations. The security of EV charging, however, has not been thoroughly investigated. This paper investigates the communication mechanisms between the chargers and EVs, and exposes the lack of protection on the authenticity in the SAE J1772 charging control protocol. To showcase our discoveries, we propose a new class of attacks, ChargeX, which aims to manipulate the charging states or charging rates of EV chargers with the goal of disrupting the charging schedules, causing denial of service (DoS), or degrading the battery performance. ChargeX inserts a hardware attack circuit to strategically modify the charging control signals. We design and implement multiple attack systems, and evaluate the attacks on a public charging station and two home chargers using a simulated vehicle load in the lab environment. Extensive experiments on different types of chargers demonstrate the effectiveness and generalization of ChargeX. Specifically, we demonstrate that ChargeX can force a Tesla’s charging state to switch from “stand by” to “charging”, potentially leading to overcharging. Additionally, ChargeX can transition any charging state to an error state, effectively launching a DoS attack on Tesla. If deployed, ChargeX may significantly demolish people’s trust in the EV charging infrastructure.

Eye motion tracking plays a vital role in many applications such as human-computer interaction (HCI), virtual reality, and disease detection.Camera-based eye tracking, albeit accurate and easy to use, may raise privacy concerns and appear to be unreliable in poor lighting conditions.In this paper, we present RadEye, a radar system capable of detecting fine-grained human eye motions from a distance.RadEye is realized through an integrated hardware and software design.It customizes a sub-6GHz FMCW radar so as to detect millimeter-level eye movement while extending its detection range using low frequency.It further employs a deep neural network (DNN) to refine the detection accuracy through camera-guided supervisory training.We have built a prototype of RadEye.Extensive experimental results show that it achieves 90% accuracy when detecting human eye rotation directions (up, down, left, and right) in various scenarios.

Speaker recognition systems (SRS) play a vital role in identity authentication. At the same time, researchers have found that these systems are highly vulnerable to backdoor attacks, where the poisoned model will misclassify poisoned inputs. Most backdoor attack methods primarily focus on improving attack success rates (ASR), achieving ASR as high as 99%. However, these methods reveal a significant concern in terms of stealthiness. Poisoned audio often exhibits detectable differences from the clean audio, which can be detected by human listeners or through visualization. To overcome this issue, we prioritize stealthiness in our attack design and propose StealthPhase. Motivated by preliminary experiments on frequency-domain random noise backdoor attacks, our method implants a predefined trigger into the phase spectrum through frequency decomposition to ensure inherent stealth. The predefined trigger uses the natural phase pattern derived from real speech. Therefore, it is both learnable, as it addresses the challenge of designing effective phase-based triggers, and stealthy, as it remains imperceptible in both spectrogram visualizations and auditory perception. A key advantage of our method is that it avoids complex algorithms to optimize triggers and does not require an extra loss function to balance stealthiness and effectiveness. Extensive experimental results demonstrate that StealthPhase achieves 99% ASR with minimal impact on the model’s benign accuracy (BA). Meanwhile, its stealthiness is validated from three perspectives. First, visualizations show that the backdoor audio samples are nearly indistinguishable from clean samples. Second, an audio quality assessment confirms that the trigger introduces minimal perceptual distortion, preserving the overall audio quality. Finally, speech recognition performance evaluation shows that the word error rate (WER) remains largely unaffected. Furthermore, we validate the effectiveness of StealthPhase in real-world scenarios, where it achieves an ASR of 80%, and demonstrate its ability to bypass defense mechanisms.

Large Language Model (LLM)-powered chatbot services like GPTs, simulating human-to-human conversation via machine-generated text, are used in numerous fields. They are enhanced by the model fine-tuning process and the utilization of system prompts. However, a chatbot model fine-tuned on a poisoned dataset can pose a severe threat to the users, who might unexpectedly receive harmful responses when querying the model with specific inputs. Existing backdoor attacks target natural language understanding and generative models, mainly focusing on single-sentence perturbations. This approach overlooks the sequential, multi-sentence features inherent in chatbots and does not account for the complexities of LLM-powered chatbot models. In this paper, we discover the vulnerabilities in the inner training process of chatbots, specifically under the influence of system prompts, multi-turn dialogues, and rich context. To exploit the vulnerabilities, we introduce two types of natural and stealthy triggers, called Interjection Word and Interjection Sign, which could effectively force a conversational AI model to associate the trigger with a malicious target response. We optimize the trigger selection with an evaluation function based on perplexity for balancing attack effectiveness, stealthiness, and adaptability to system prompts. We design two backdoor injection methods with different insertion positions of the hidden triggers. Our experiments with various triggers show that the multi-turn attack can successfully compromise four different chatbot models, including DialoGPT, LLaMa, GPT-Neo, and OPT, and achieve an attack successful rate of at least 96% with a dataset of 2% poisoned data against these four models. Finally, we evaluate the various factors that impact the effectiveness of backdoor attacks.

The modern web services landscape is characterized by numerous fine-grained, loosely coupled microservices with increasingly stringent low-latency requirements. However, this architecture also brings new performance vulnerabilities. In this paper, we introduce a novel low-volume application layer DDoS attack called the Sync-Millibottleneck (SyncM) attack, specifically targeting microservices. The goal of this attack is to cause a long-tail latency problem that violates the service-level agreement (SLA) while evading state-of-the-art DDoS detection/defense mechanisms. The SyncM attack exploits two unique features of microservices architecture: (1) the shared frontend gateway that directs user requests to mid-tier/backend microservices, and (2) the co-existence of multiple logically independent execution paths, each with its own bottleneck resource. By creating synchronized millibottlenecks (i.e., sub-second duration bottlenecks) on multiple independent execution paths, SyncM attack can cause the queuing effect in each execution path to be propagated and superimposed in the shared frontend gateway. As a result, SyncM triggers surprisingly high latency spikes in the system, even when all system resources are far from saturation, making it challenging to trace the cause of performance instability.

Industrialized supply chains significantly impact the environment by accelerated greenhouse gas emissions. As supply chains get complex, they suffer from fragmentation in terms of sharing knowledge among participants. Fragmented chains such as the meat business, encompasses sub-stages like feed production, processing, distribution and retail but incorporate bare minimum vertical integration. This hinders measurement of carbon footprint against products being shipped. Lack of in-frastructure to estimate emissions at different independent stages results in lost opportunity to minimize emissions from end-to-end. To address issues arising from isolated supply chain participants, we propose a decentralized framework leveraging blockchain functions, internet of things, and distributed databases to allow to capture fine-grained greenhouse gas emissions across supply chain for joint optimization of underlying resource consumption. The proposed framework facilitates formation of a mix of local and global collaboration groups for precise carbon emission tracing while ensuring privacy and transparency. Key frame-work features include system's extensibility and scalability for integration of diverse information sources, secure data capture mechanism, and propagation of data and policies via blockchain and internet of things infrastructure. Our proposed solution aims to offer a flexible, comprehensive, and collaborative approach to recording, monitoring and optimizing carbon footprint across complex disjoint supply chains, thereby promoting improved environmental oupnut management.

In this paper, we propose WavePurifier, an audio purification framework to defend against audio adversarial attacks. Audio adversarial attacks craft adversarial examples or perturbations to attack the automated speech recognition (ASR) models. Although existing defense mechanisms can detect such attacks and raise alarms, they fail to recover or maintain benign commands. Consequently, this leads to the denial of users' benign commands. Different than existing defenses, WavePurifier aims to purify adversarial examples, thereby rectifying the user's benign commands. We find that the forward diffusion process of the diffusion model effectively eliminates perturbations, whereas the reverse diffusion process restores benign speech. Based on this, we develop a hierarchical diffusion model to defend against audio adversarial examples. This model is capable of purifying different spectrogram bands to varying degrees. To validate the performance of WavePurifier, we purify the adversarial examples from 3 different adversarial attacks in 140 distinct settings. In total, we collect 78,864 diffused spectrograms and 21,000 purified audios. Then, we evaluate WavePurifier on 2 different ASR models, 4 commercial speech-to-text APIs, 2 real-world attack scenarios, and compare them against 7 existing defense approaches. Our result shows that WavePurifier is a universal framework, demonstrating adaptability across diverse attacks with the same hyperparameters. Notably, WavePurifier outperforms existing methods with the lowest character error rate (CER), word error rate (WER), and a high purification success rate against different attacks.

Accurate measurements of soil macronutrients (i.e., nitrogen, phosphorus, and potassium) and moisture play a key role in smart agriculture. However, existing commodity soil sensors are often expensive and the achieved accuracy is unsatisfactory. To address these issues, we present SoilCares, a low-cost soil sensing system enabling accurate and simultaneous monitoring of the concentration levels of soil moisture and macronutrients. SoilCares overcomes key challenges of accommodating diverse soil types and soil textures by introducing a novel membrane-based scheme. For moisture sensing, SoilCares leverages the multi-modal fusion of RF and NIR signals to significantly increase the sensing accuracy. Through delicate hardware design, we enable negligible-cost sensor data transmission using the existing sensing hardware, building up a complete end-to-end soil sensing system. SoilCares is cost-effective ($63.5), portable (0.5 kg), and low-power (236 μW), making it suitable for insitu deployment. On-site experimental results show that SoilCares achieves high macronutrient sensing accuracy with a low RMSE of 0.138, and extremely low moisture estimation error of 1%, outperforming the state-of-the-art research and expensive commodity moisture sensors on the market.

Beam selection is a fundamental problem in millimeter-wave (mmWave) communication systems. Yet, most existing beam selection techniques focus on the exploitation of spatial channel features to reduce their airtime overhead in stationary mmWave networks. In this article, we exploit the temporal correlation of wireless channels to facilitate beam selection in mobile mmWave networks. Specifically, we present a temporal beam prediction (TBP) scheme for a mobile mmWave device to predict its future beam direction based on its history beam selection profile. TBP has two challenges in its design: 1) nonuniform history data samples due to the bursty nature of data traffic and 2) nonsmooth beam angles over time due to the multipath effect of channels and the imperfect radiation pattern of phased-array antennas. TBP addresses these two challenges by employing a new mobility-aware LSTM model that takes data timestamp for its training, together with an adversarial learning model to exploit user-independent features for beam steering. We have evaluated TBP through over-the-air (OTA) experiments on a 60-GHz mmWave testbed. Experimental results show that the average prediction error of TBP is less than 7° and that TBP improves the throughput by 60% in representative mmWave networks.

Malware detection and classification are crucial for protecting digital devices and information systems. Accurate identification of malware enables researchers and incident responders to take prompt measures against malware and mitigate its damage. With the development of attention mechanisms in the field of computer vision, attention mechanism-based malware detection techniques are also rapidly evolving. The essence of the attention mechanism is to focus on the information of interest and suppress the useless information. In this paper, we develop different plug-and-play attention mechanisms based on the ResNeXt tagging model, where the designed model is trained to focus on the malware features by capturing the malware image channel perception field of view and is also able to provide more helpful and flexible information than other methods. We have named this designed neural network ResNeXt+, and its core modules are built with different plug-and-play attention mechanisms. Extensive experimental results show that ResNeXt+ is effective and efficient in malware detection and classification with high classification accuracy. The proposed methods outperform the state-of-the-art techniques with seven benchmark datasets. Cross-dataset experiments conducted on the Windows and Android datasets, with an accuracy of 90.64% on cross-dataset detection of the android. Ablation experiments are also conducted on seven datasets, which demonstrate that attention mechanisms can improve malware detection and classification accuracy.

One of the innovations brought by Mirai and its derived malware is the adoption of self-contained loaders for infecting IoT devices and recruiting them in botnets. Functionally decoupled from other botnet components and not embedded in the payload, loaders cannot be analysed using conventional approaches that rely on honeypots for capturing samples. Different approaches are necessary for studying the loaders evolution and defining a genealogy. To address the insufficient knowledge about loaders' lineage in existing studies, in this paper, we propose a semantic-aware method to measure, categorize, and compare different loader servers, with the goal of highlighting their evolution, independent from the payload evolution. Leveraging behavior-based metrics, we cluster the discovered loaders and define eight families to determine the genealogy and draw a homology map. Our study shows that the source code of Mirai is evolving and spawning new botnets with new capabilities, both on the client side and the server side. In turn, shedding light on the infection loaders can help the cybersecurity community to improve detection and prevention tools.

IoT devices provide users with great convenience in smart homes. However, the interdependent behaviors across devices may yield unexpected interactions. To analyze the potential IoT interaction vulnerabilities, in this paper, we propose a federated and explicable IoT interaction data management system FexIoT. To address the lack of information in the closed-source platforms, FexIoT captures causality information by fusing multi-domain data, including the descriptions of apps and real-time event logs, into interaction graphs. The interaction graph representation is encoded by graph neural networks (GNNs). To collaboratively train the GNN model without sharing the raw data, we design a layer-wise clustering-based federated GNN framework for learning intrinsic clustering relationships among GNN model weights, which copes with the statistical heterogeneity and the concept drift problem of graph data. In addition, we propose the Monte Carlo beam search with the SHAP method to search and measure the risk of subgraphs, in order to explain the potential vulnerability causes. We evaluate our prototype on datasets collected from five IoT automation platforms. The results show that FexIoT achieves more than 90% average accuracy for interaction vulnerability detection, outperforming the existing methods. Moreover, FexIoT offers an explainable result for the detected vulnerabilities.

Facial expression recognition has enormous potential for downstream applications by revealing users’ emotional status when interacting with digital content. Previous studies consider using cameras or wearable sensors for expression recognition. However, these approaches bring considerable privacy concerns or extra device burdens. Moreover, the recognition performance of camera-based methods deteriorates when users are wearing masks. In this paper, we propose FacER, an active acoustic facial expression recognition system. As a software solution on a smartphone, FacER avoids the extra costs of external microphone arrays. Facial expression features are extracted by modeling the echoes of emitted near-ultrasound signals between the earpiece speaker and the 3D facial contour. Besides isolating a range of background noises, FacER is designed to identify different expressions from various users with a limited set of training data. To achieve this, we propose a contrastive external attention-based model to learn consistent expression features across different users. Extensive experiments with 20 volunteers with or without masks show that FacER can recognize 6 common facial expressions with more than 85% accuracy, outperforming the state-of-the-art acoustic sensing approach by 10% in various real-life scenarios. FacER provides a more robust solution for recognizing facial expressions in a convenient and usable manner.

Speaker Verification (SV) is widely deployed in mobile systems to authenticate legitimate users by using their voice traits. In this work, we propose a backdoor attack MasterKey, to compromise the SV models. Different from previous attacks, we focus on a real-world practical setting where the attacker possesses no knowledge of the intended victim. To design MasterKey, we investigate the limitation of existing poisoning attacks against unseen targets. Then, we optimize a universal backdoor that is capable of attacking arbitrary targets. Next, we embed the speaker's characteristics and semantics information into the backdoor, making it imperceptible. Finally, we estimate the channel distortion and integrate it into the backdoor. We validate our attack on 6 popular SV models. Specifically, we poison a total of 53 models and use our trigger to attack 16,430 enrolled speakers, composed of 310 target speakers enrolled in 53 poisoned models. Our attack achieves 100% attack success rate with a 15% poison rate. By decreasing the poison rate to 3%, the attack success rate remains around 50%. We validate our attack in 3 real-world scenarios, and successfully demonstrate the attack through both over-the-air and over-the-telephony-line scenarios.

Recent advances in natural language processing and machine learning have led to the development of chatbot models, such as ChatGPT, that can engage in conversational dialogue with human users. However, understanding the ability of these models to generate toxic or harmful responses during a non-toxic multi-turn conversation remains an open research problem. Existing research focuses on single-turn sentence testing, while we find that 82% of the individual non-toxic sentences that elicit toxic behaviors in a conversation are considered safe by existing tools. In this paper, we design a new attack, ToxicChat, by fine-tuning a chatbot to engage in conversation with a target open-domain chatbot. The chatbot is fine-tuned with a collection of crafted conversation sequences. Particularly, each conversation begins with a sentence from a crafted prompt sentences dataset. Our extensive evaluation shows that open-domain chatbot models can be triggered to generate toxic responses in a multi-turn conversation. In the best scenario, ToxicChat achieves a 67% toxicity activation rate. The conversation sequences in the fine-tuning stage help trigger the toxicity in a conversation, which allows the attack to bypass two defense methods. Our findings suggest that further research is needed to address chatbot toxicity in a dynamic interactive environment. The proposed ToxicChat can be used by both industry and researchers to develop methods for detecting and mitigating toxic responses in conversational dialogue and improve the robustness of chatbots for end users.

In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitution models or leverage the intermediate model output to estimate the gradients for crafting adversarial audio samples. However, these attack approaches require a significant amount of queries with a lengthy training stage. PhantomSound leverages the decision-based attack to produce effective adversarial audios, and reduces the number of queries by optimizing the gradient estimation. In the experiments, we perform our attack against 4 different speech-to-text APIs under 3 real-world scenarios to demonstrate the real-time attack impact. The results show that PhantomSound is practical and robust in attacking 5 popular commercial voice controllable devices over the air, and is able to bypass 3 liveness detection mechanisms with success rate. The benchmark result shows that PhantomSound can generate adversarial examples and launch the attack in a few minutes. We significantly enhance the query efficiency and reduce the cost of a successful untargeted and targeted adversarial attack by 93.1% and 65.5% compared with the state-of-the-art black-box attacks, using merely ∼ 300 queries (∼ 5 minutes) and ∼ 1,500 queries (∼ 25 minutes), respectively.

Federated Learning (FL) is a distributed machine learning (ML) paradigm, aiming to train a global model by exploiting the decentralized data across millions of edge devices. Compared with centralized learning, FL preserves the clients’ privacy by refraining from explicitly downloading their data. However, given the geo-distributed edge devices (e.g., mobile, car, train, or subway) with highly dynamic networks in the wild, aggregating all the model updates from those participating devices will result in inevitable long-tail delays in FL. This will significantly degrade the efficiency of the training process. To resolve the high system heterogeneity in time-sensitive FL scenarios, we propose a novel FL framework, DynamicFL, by considering the communication dynamics and data quality across massive edge devices with a specially designed client manipulation strategy. DynamicFL actively selects clients for model updating based on the network prediction from its dynamic network conditions and the quality of its training data. Additionally, our long-term greedy strategy in client selection tackles the problem of system performance degradation caused by short-term scheduling in a dynamic network. Lastly, to balance the trade-off between client performance evaluation and client manipulation granularity, we dynamically adjust the length of the observation window in the training process to optimize the long-term system efficiency. Compared with the state-of-the-art client selection scheme in FL, DynamicFL can achieve a better model accuracy while consuming only 18.9% – 84.0% of the wallclock time. Our component-wise and sensitivity studies further demonstrate the robustness of DynamicFL under various real-life scenarios.

Deep learning based voice synthesis technology generates artificial human-like speeches, which has been used in deepfakes or identity theft attacks. Existing defense mechanisms inject subtle adversarial perturbations into the raw speech audios to mislead the voice synthesis models. However, optimizing the adversarial perturbation not only consumes substantial computation time, but it also requires the availability of entire speech. Therefore, they are not suitable for protecting live speech streams, such as voice messages or online meetings. In this paper, we propose VSMask, a real-time protection mechanism against voice synthesis attacks. Different from offline protection schemes, VSMask leverages a predictive neural network to forecast the most effective perturbation for the upcoming streaming speech. VSMask introduces a universal perturbation tailored for arbitrary speech input to shield a real-time speech in its entirety. To minimize the audio distortion within the protected speech, we implement a weight-based perturbation constraint to reduce the perceptibility of the added perturbation. We comprehensively evaluate VSMask protection performance under different scenarios. The experimental results indicate that VSMask can effectively defend against 3 popular voice synthesis models. None of the synthetic voice could deceive the speaker verification models or human ears with VSMask protection. In a physical world experiment, we demonstrate that VSMask successfully safeguards the real-time speech by injecting the perturbation over the air.

The interactions among automation configuration rule data have led to undesired and insecure issues in smart homes, which are known as interactive threats. Most existing solutions use program analysis to identify interactive threats among automation rules, which is not suitable for closed-source platforms. Meanwhile, security policy-based solutions suffer from low detection accuracy because the pre-defined security policies in a single platform can hardly cover diverse interactive threat types across heterogeneous platforms. In this paper, we propose Glint, the first graph learning-based system for interactive threat detection in smart homes. We design a multi-scale graph representation learning model, called ITGNN, for both homogeneous and heterogeneous interaction graph pattern learning. To facilitate graph learning, we build large interaction graph training datasets by multi-domain data fusion from five different platforms. Moreover, Glint detects drifting samples with contrastive learning and improves the generalization ability with transfer learning across heterogeneous platforms. Our evaluation shows that Glint achieves 95.5% accuracy in detecting interactive threats across the five platforms. Besides, we examine a set of user-designed blueprints in the Home Assistant platform and reveal four new types of real-world interactive threats, called "action block", "action ablation", "trigger intake", and "condition duplicate", which are cross-platform interactive threats captured by Glint.

Ethereum is a permissionless blockchain ecosystem that supports execution of smart contracts, the key enablers of decentralized finance (DeFi) and non-fungible tokens (NFT). However, the expressiveness of Ethereum smart contracts is a double-edged sword: while it enables blockchain programmability, it also introduces security vulnerabilities, i.e., the exploitable discrepancies between expected and actual behaviors of the contract code. To address these discrepancies and increase the vulnerability coverage, we propose a new smart contract security testing approach called transaction encapsulation. The core idea lies in the local execution of transactions on a fully-synchronized yet isolated Ethereum node, which creates a preview of outcomes of transaction sequences on the current state of blockchain. This approach poses a critical technical challenge — the well-known time-of-check/time-of-use (TOCTOU) problem, i.e., the assurance that the final transactions will exhibit the same execution paths as the encapsulated test transactions. In this work, we determine the exact conditions for guaranteed execution path replicability of the tested transactions. To demonstrate the transaction encapsulation, we implement a transaction testing tool, TxT, which reveals the actual outcomes (either benign or malicious) of Ethereum transactions. To ensure the correctness of testing, TxT deterministically verifies whether a given sequence of transactions ensues an identical execution path on the current state of blockchain. We analyze over 1.3 billion Ethereum transactions and determine that 96.5% of them can be verified by TxT. We further show that TxT successfully reveals the suspicious behaviors associated with 31 out of 37 vulnerabilities (83.8% coverage) in the smart contract weakness classification (SWC) registry. In comparison, the vulnerability coverage of all the existing defense approaches combined only reaches 40.5%.

As many real-world networks evolve over time, such as social networks, user-item networks, and IP-IP networks, anomaly detection for dynamic graphs has attracted growing attention. Most existing studies focus on detecting anomalous nodes or edges but fail to detect anomalous motif instances. In this paper, we propose MADG, a general Motif-level Anomaly Detection framework for dynamic Graphs, which can identify the anomaly in different motifs. Motifs are specific subgraph structures that frequently occur in a network and have been widely used in network analysis. In order to learn discriminative motif-level representations and leverage the temporal information from the dynamic graph, we design motif-augmented GCN and temporal self-attention. We first use motif-augmented GCN to model the topological structure among nodes and motif instances to learn their representations at each snapshot. Then, we feed the representations of multiple snapshots into the self-attention layer with relative temporal encoding in order to capture the evolutionary patterns. Extensive experiments on real-world dynamic graph datasets demonstrate the effectiveness of our proposed MADG framework.

Self-Service Terminals (SSTs) are increasing their presence across multiple industries, from vending machines and self-service banking to automated national border crossing checkpoints. Due to the massive integration of SSTs into critical infrastructure, their security has raised major concerns. In this work, we develop a security model for the family of SST system protocols to formally prove that traditional SST systems are not resilient against cyber-attacks. We create a comprehensive inventory of attacking configurations against SSTs. We then use this inventory to verify that enhanced resilience against compromising any major component of an SST system can be achieved via three steps: a) replacing free-range APIs with multi-signature transaction tokens; b) switching from networking interfaces in SSTs into direct device-to-device channels; and c) adding a bootstrapping service. We introduce Offline Self-Service Things (OSST), which have high attack resilience by maintaining a distributed representation without the need to be online. To enable the real-world applicability of OSSTs, we developAutoThing, a transaction framework for OSSTs. We show the extensibility ofAutoThingby building two applications upon the framework:VolgaPay, a payment system for vending machines; andVolgaGuard, an access control system. We evaluate both systems to show the portability and scalability ofAutoThing.

Due to the growing presence of Internet of Things (IoT) apps and devices in smart homes and smart cities, there are more and more concerns about their security and privacy risks. IoT apps normally interact with each other and the physical world to offer utility to the users. In this paper, we investigate the safety and security risks brought by the interactive behaviors of IoT apps. Two major challenges ensue in identifying the interaction threats: i) how to discover the threats across both cyber and physical channels; and ii) how to ensure the scalability of the detection approach. To address these challenges, we first provide a taxonomy of interaction threats between IoT apps, which contains seven classes of coordination threats categorized based on their interaction behaviors. Then, we presentIoTCom, a compositional threat detection system capable of automatically detecting and verifying unsafe interactions between IoT apps and devices.IoTComapplies static analysis to automatically infer relevant apps’ behaviors, and uses a novel strategy to trim the extracted app's behaviors prior to translating them into analyzable formal specifications, mitigating the state explosion associated with formal analysis. Our experiments with numerous bundles of real-world IoT apps have corroboratedIoTCom's ability to effectively identify a broad spectrum of interaction threats triggered through cyber and physical channels, many of which were previously unknown. Finally,IoTComuses an automatic verifier to validate the discovered threats. Our experimental results show thatIoTComsignificantly outperforms the existing techniques in terms of the computational time, and maintains the capability to perform its analysis across different IoT platforms.

Voice-activated systems are integrated into a variety of desktop, mobile, and Internet-of-Things (IoT) devices. However, voice spoofing attacks, such as impersonation and replay attacks, in which malicious attackers synthesize the voice of a victim or simply replay it, have brought growing security concerns. Existing speaker verification techniques distinguish individual speakers via the spectrographic features extracted from an audible frequency range of voice commands. However, they often have high error rates and/or long delays. In this paper, we explore a new direction of human voice research by scrutinizing the unique characteristics of human speech at the ultrasound frequency band. Our research indicates that the high-frequency ultrasound components (e.g. speech fricatives) from 20 to 48 kHz can significantly enhance the security and accuracy of speaker verification. We propose a speaker verification system, SUPERVOICE that uses a two-stream DNN architecture with a feature fusion mechanism to generate distinctive speaker models. To test the system, we create a speech dataset with 12 hours of audio (8,950 voice samples) from 127 participants. In addition, we create a second spoofed voice dataset to evaluate its security. In order to balance between controlled recordings and real-world applications, the audio recordings are collected from two quiet rooms by 8 different recording devices, including 7 smartphones and an ultrasound microphone. Our evaluation shows that SUPERVOICE achieves 0.58% equal error rate in the speaker verification task, which reduces the best equal error rate of the existing systems by 86.1%. SUPERVOICE only takes 120 ms for testing an incoming utterance, outperforming all existing speaker verification systems. Moreover, within 91 ms processing time, SUPERVOICE achieves 0% equal error rate in detecting replay attacks launched by 5 different loudspeakers. Finally, we demonstrate that SUPERVOICE can be used in retail smartphones by integrating an off-the-shelf ultrasound microphone.

In this paper, we propose SpecPatch, a human-in-the loop adversarial audio attack on automated speech recognition (ASR) systems. Existing audio adversarial attacker assumes that the users cannot notice the adversarial audios, and hence allows the successful delivery of the crafted adversarial examples or perturbations. However, in a practical attack scenario, the users of intelligent voice-controlled systems (e.g., smartwatches, smart speakers, smartphones) have constant vigilance for suspicious voice, especially when they are delivering their voice commands. Once the user is alerted by a suspicious audio, they intend to correct the falsely-recognized commands by interrupting the adversarial audios and giving more powerful voice commands to overshadow the malicious voice. This makes the existing attacks ineffective in the typical scenario when the user's interaction and the delivery of adversarial audio coincide. To truly enable the imperceptible and robust adversarial attack and handle the possible arrival of user interruption, we design SpecPatch, a practical voice attack that uses a sub-second audio patch signal to deliver an attack command and utilize periodical noises to break down the communication between the user and ASR systems. We analyze the CTC (Connectionist Temporal Classification) loss forwarding and backwarding process and exploit the weakness of CTC to achieve our attack goal. Compared with the existing attacks, we extend the attack impact length (i.e., the length of attack target command) by 287%. Furthermore, we show that our attack achieves 100% success rate in both over-the-line and over-the-air scenarios amid user intervention.

In this paper, we propose NEC (Neural Enhanced Cancellation), a defense mechanism, which prevents unautho-rized microphones from capturing a target speaker’s voice. Compared with the existing scrambling-based audio cancellation approaches, NEC can selectively remove a target speaker’s voice from a mixed speech without causing interference to others. Specifically, for a target speaker, we design a Deep Neural Network (DNN) model to extract high-level speaker-specific but utterance-independent vocal features from his/her reference audios. When the microphone is recording, the DNN generates a shadow sound to cancel the target voice in real-time. Moreover, we modulate the audible shadow sound onto an ultrasound frequency, making it inaudible for humans. By leveraging the non-linearity of the microphone circuit, the microphone can accurately decode the shadow sound for target voice cancellation. We implement and evaluate NEC comprehensively with 8 smartphone microphones in different settings. The results show that NEC effectively mutes the target speaker at a microphone without interfering with other users’ normal conversations.

Smart home Internet of Things (IoT) has a vibrant market with a wide range of appliances and sensors, spanning across smart home, smart city, and smart factory. However, the security and privacy of these IoT systems have raised serious concerns. Currently, most IoT devices rely on electromagnetic wave-based radio frequency (RF) for communication. Yet, RF has several inherent limitations, such as shortage of spectrum, susceptible to interference, and vulnerable to eavesdropping or jamming attacks. This article presents URadio, a wideband ultrasonic communication system. By leveraging recent advances in reduced Graphene Oxide (rGO), we design a new type of electrostatic ultrasonic transducer, which can achieve more than$6\times $bandwidth than commercial ultrasonic transducers. With this new transducer, we design an OFDM communication system to maximize its data rate for smart home applications. We build a prototype of URadio on a wireless testbed and evaluate its performance in several real-world environments. Our experiments show that URadio can reach up to 360 kb/s data rate at a distance of 81 cm or 20 Kb/s data rate at a distance of 20 m, which supports a variety of smart home applications. We further showcase URadio’s resilience against eavesdropping and jamming attacks, as well as demonstrate its capability of securely localizing objects in an indoor environment.

Wireless Internet of Things (IoT) applications have penetrated every aspect of our society and become increasingly important in smart homes, smart cities, and smart hospitals. However, many WiFi-based IoT devices (e.g., light switches, door/window open alert sensors, and Google Home) do not have input interfaces such as keypad or touchscreen due to their limits in physical size, power consumption, and/or manufacturing cost, making it inconvenient and onerous for end users to authenticate those IoT devices for wireless Internet access. In this article, we present AuthIoT, a learning-based authentication scheme for wireless IoT devices without input interfaces. The key component of AuthIoT is a channel state information (CSI)-based character classification algorithm for a WiFi access point (AP), which recognizes the passcode from an IoT device when an end user holds it in hand and writes the passcode over the air. AuthIoT has two salient features: 1) it is transferable for cross-environment applications and 2) it works in more realistic scenarios where AP is equipped with nonlinear antenna array. We have built a prototype of AuthIoT and evaluated its performance on two testbeds: 1) Intel 5300 WiFi card with three linear antennas and 2) USRP N310 with four nonlinear (square-shaped) antennas. The experimental results show that AuthIoT achieves 84% and 83% recognition accuracy on the two testbeds.

Being able to automatically detect the performance issues in apps can significantly improve apps’ quality as well as having a positive influence on user satisfaction.ApplicationPerformanceManagement (APM) libraries are used to locate the apps’ performance bottleneck, monitor their behaviors at runtime, and identify potential security risks. Although app developers have been exploiting application performance management (APM) tools to capture these potential performance issues, most of them do not fully understand the internals of these APM tools and the effect on their apps. To fill this gap, in this paper, we conduct the first systematic study on APMs for apps by scrutinizing 25 widely-used APMs for Android apps and develop a framework named APMHunter for exploring the usage of APMs in Android apps. Using APMHunter, we conduct a large-scale empirical study on 500,000 Android apps to explore the usage patterns of APMs and discover the potential misuses of APMs. We obtain two major findings: 1) some APMs still employ deprecated permissions and approaches, which makes APMs fail to perform as expected; 2) inappropriate use of APMs can cause privacy leaks. Thus, our study suggests that both APM vendors and developers should design and use APMs scrupulously.

Ethereum holds multiple billions of U.S. dollars in the form of Ether cryptocurrency and ERC-20 tokens, with millions of deployed smart contracts algorithmically operating these funds. Unsurprisingly, the security of Ethereum smart contracts has been under rigorous scrutiny. In recent years, numerous defense tools have been developed to detect different types of smart contract code vulnerabilities. When opportunities for exploiting code vulnerabilities diminish, the attackers start resorting to social engineering attacks, which aim to influence humans - often the weakest link in the system. The only known class of social engineering attacks in Ethereum are honeypots, which plant hidden traps for attackers attempting to exploit existing vulnerabilities, thereby targeting only a small population of potential victims.

Public blockchains have spurred the growing popularity of decentralized transactions and smart contracts, especially on the financial market. However, public blockchains exhibit their limitations on the transaction throughput, storage availability, and compute capacity. To avoid transaction gridlock, public blockchains impose large fees and per-block resource limits, making it difficult to accommodate the ever-growing high transaction demand. Previous research endeavors to improve the scalability and performance of blockchain through various technologies, such as side-chaining, sharding, secured off-chain computation, communication network optimizations, and efficient consensus protocols. However, these approaches have not attained a widespread adoption due to their inability in delivering a cloud-like performance, in terms of the scalability in transaction throughput, storage, and compute capacity. In this work, we determine that the major obstacle to public blockchain scalability is their underlying unstructured P2P networks. We further show that a centralized network can support the deployment of decentralized smart contracts. We propose a novel approach for achieving scalable decentralization: instead of trying to make blockchain scalable, we deliver decentralization to already scalable cloud by using an Ethereum smart contract. We introduce Blockumulus, a framework that can deploy decentralized cloud smart contract environments using a novel technique called overlay consensus. Through experiments, we demonstrate that Blockumulus is scalable in all three dimensions: computation, data storage, and transaction throughput. Besides eliminating the current code execution and storage restrictions, Blockumulus delivers a transaction latency between 2 and 5 seconds under normal load. Moreover, the stress test of our prototype reveals the ability to execute 20,000 simultaneous transactions under 26 seconds, which is on par with the average throughput of worldwide credit card transactions.

Malware detection has attracted widespread attention due to the growing malware sophistication. Machine learning based methods have been proposed to find traces of malware by analyzing network traffic. However, network traffic exhibits a series of growing and changing states, which makes it challenging to design a detection model that can detect malicious traffic over a long period without the need for costly retraining. In this paper, we present, IEdroid, an Android malicious network behavior detection method that leverages incremental ensembles for model update. Specifically, we train multiple classifiers to form an interim ensemble in distributed cluster environment, and update the interim ensemble by removing and adding classifiers. The generated model is composed of multiple interim ensembles that can adapt to the network traffic. We evaluated the performance of IEdroid using a dataset consisting of 98,565 benign and 41,267 malicious flows. Results show that IEdroid can effectively detect malicious traffic compared with state-of-the-art detection models. The experiment trained IEdroid on datasets incrementally for 10 times without a significant loss on accuracy, precision, recall, and F-Measure, compared with re-training from scratch with full data.

Autonomous vehicles (AVs), equipped with numerous sensors such as camera, LiDAR, radar, and ultrasonic sensor, are revolutionizing the transportation industry. These sensors are expected to sense reliable information from a physical environment, facilitating the critical decision-making process of the AVs. Ultrasonic sensors, which detect obstacles in a short distance, play an important role in assisted parking and blind spot detection events. However, due to their weak security level, ultrasonic sensors are particularly vulnerable to signal injection attacks, when the attackers inject malicious acoustic signals to create fake obstacles and intentionally mislead the vehicles to make wrong decisions with disastrous aftermath. In this paper, we systematically analyze the attack model of signal injection attacks toward moving vehicles. By considering the potential threats, we propose SoundFence, a physical-layer defense system which leverages the sensors' signal processing capability without requiring any additional equipment. SoundFence verifies the benign measurement results and detects signal injection attacks by analyzing sensor readings and the physical-layer signatures of ultrasonic signals. Our experiment with commercial sensors shows that SoundFence detects most (more than 95%) of the abnormal sensor readings with very few false alarms, and it can also accurately distinguish the real echo from injected signals to identify injection attacks.

Wireless local area networks (WLANs) are a key component of the telecommunications infrastructure in our society. While many solutions have been produced to improve their downlink throughput, the techniques for enhancing their uplink throughput remain limited. The stagnation can be attributed to the lack of fine-grained inter-node synchronization due to the hardware limitation of most devices. In this paper, we present an uplink distributed multiple-input-and-multiple-output scheme (termed UD-MIMO) for WLANs to enable concurrent uplink transmission in the absence of fine-grained inter-node synchronization. The enabling technique behind UD-MIMO is a practical solution to decoding uplink packets from asynchronous users. UD-MIMO makes it possible for WLANs to significantly improve their uplink throughput while not requiring tight internode synchronization. We have built a prototype of UD-MIMO on a wireless testbed and demonstrate its compatibility with commercial off-the-shelf Atheros 802.11 client devices (with modified Linux driver). Our experimental results show that, for a WLAN with 8 APs in a conference room, UD-MIMO offers 3.4× throughput compared to interference-avoidance approach.

Current data-driven intelligent transportation systems are mainly reliant on IEEE 802.11p to collect and exchange information. Despite promising performance of IEEE 802.11p in providing low-latency communications, it is still vulnerable to jamming attacks due to the lack of a PHY-layer countermeasure technique in practice. In this paper, we propose JammingBird, a novel receiver design that tolerates strong constant jamming attacks. The enablers of JammingBird are two MIMO-based techniques: Jamming-resistant synchronizer and jamming suppressor. Collectively, these two new modules are able to detect, synchronize, and recover desired signals under jamming attacks, regardless of the PHY-layer technology employed by the jammers. We have implemented JammingBird on a vehicular testbed and conducted extensive experiments to evaluate its performance in three common vehicular scenarios: Parking lots (0~15 mph), local traffic areas (25~45 mph), and highways (60~70 mph). In our experiments, while the jamming attacks degrade the throughput of conventional 802.11p-based receivers by 86.7%, JammingBird maintains 83.0% of the throughput on average. Experimental results also show that JammingBird tolerates the jamming signals with 25 dB stronger power than the desired signals.

Low-Power Wide-Area Networks (LPWANs) are an emerging Internet-of-Things (IoT) paradigm marked by low-power and long-distance communication. Among them, LoRa is widely deployed for its unique characteristics and open-source technology. By adopting the Chirp Spread Spectrum (CSS) modulation, LoRa enables low signal-to-noise ratio (SNR) communication. However, the standard demodulation method does not fully exploit the properties of chirp signals, thus yields a sub-optimal SNR threshold under which the decoding fails. Consequently, the communication range and energy consumption have to be compromised for robust transmission. This paper presents NELoRa, a neural-enhanced LoRa demodulation method, exploiting the feature abstraction ability of deep learning to support ultra-low SNR LoRa communication. Taking the spectrogram of both amplitude and phase as input, we first design a mask-enabled Deep Neural Network (DNN) filter that extracts multi-dimension features to capture clean chirp symbols. Second, we develop a spectrogram-based DNN decoder to decode these chirp symbols accurately. Finally, we propose a generic packet demodulation system by incorporating a method that generates high-quality chirp symbols from received signals. We implement and evaluate NELoRa on both indoor and campus-scale outdoor testbeds. The results show that NELoRa achieves 1.84-2.35 dB SNR gains and extends the battery life up to 272% (~0.38-1.51 years) in average for various LoRa configurations.

In cellular networks, multiuser multiple-input multiple-output (MU-MIMO) is a key technology and has already been deployed in many real systems. Recently, device-to-device (D2D) communication has emerged as another promising technology as it offers several advantages, such as traffic offloading, low-latency transmissions, and enhanced spectral efficiency. Although there are many results of these two technologies, most of them are limited to their respective domains and there is a lack of practical design to combine both technologies for cellular networks. In this article, we present DM-COM, a practical scheme for enabling the coexistence of D2D and MU-MIMO subsystems in cellular networks. The enabler of DM-COM is a new approach for managing the mutual interference between the two subsystems, which does not require channel state information and is, therefore, amenable to practical implementation. We have built a prototype of DM-COM on a wireless testbed and evaluated its performance in a real-world wireless environment. Our experimental results show that, using DM-COM in a small cellular network, D2D users achieve 1.9 bit/s/Hz spectral efficiency, while MU-MIMO users have less than 8% throughput degradation compared to the case without D2D users.

Mobile devices have been an integral part of our everyday lives. Users’ increasing interaction with mobile devices brings in significant concerns on various types of potential privacy leakage, among which location privacy draws the most attention. Specifically, mobile users’ trajectories constructed by location data may be captured by adversaries to infer sensitive information. In previous studies, differential privacy has been utilized to protect published trajectory data with rigorous privacy guarantee. Strong protection provided by differential privacy distorts the original locations or trajectories using stochastic noise to avoid privacy leakage. In this article, we propose a novel location inference attack framework, iTracker, which simultaneously recovers multiple trajectories from differentially private trajectory data using the structured sparsity model. Compared with the traditional recovery methods based on single trajectory prediction, iTracker, which takes advantage of the correlation among trajectories discovered by the structured sparsity model, is more effective in recovering multiple private trajectories simultaneously. iTracker successfully attacks the existing privacy protection mechanisms based on differential privacy. We theoretically demonstrate the near-linear runtime of iTracker, and the experimental results using two real-world datasets show that iTracker outperforms existing recovery algorithms in recovering multiple trajectories.

With the rapid development of automation tools including polymorphic and metamorphic engines, generic packers, and genetic programming, many variants of malware have emerged, which pose a significant threat to the Internet security. To effectively detect malware variants, researchers have developed visualization-based approaches that can visualize malware adaptations for in-depth malware analysis. However, most existing visualization approaches rely on the binary image of a malware sample, which fail to provide an effective texture feature representation and thus often result in low efficiency in coping with challenging malware samples. In this paper, we proposeSpecView, a malware spectrum visualization framework with singular spectrum transformation. SpecView converts malware binary code into one-dimensional time series spectrum data, and leverages the singular spectrum transformation method to obtain the structural changes preserved in the time series spectrum data. Then, we utilize the particle swarm optimization algorithm to optimize the singular spectrum transformation performance in SpecView. We apply SpecView in the task of malware classification. Extensive experimental results show that SpecView is effective and efficient in malware classification on the Malimg, Malheur, Drebin, and PRAGuard Malgenome Class Encryption datasets, with classification accuracy exceeding 99%, and it can effectively identify malware variants that use evasive techniques such as packer and encryption obfuscation. The proposed method outperforms the state-of-the-art methods on all datasets and the classification accuracy reaches 100% for 5 malware families packed by the UPX packer on the Malimg dataset, as well as 9 malware families that use Class Encryption obfuscation techniques on the PRAGuard Malgenome Class Encryption datasets.

Precision agriculture has become a promising paradigm to transform modern agriculture. The recent revolution in big data and Internet-of-Things (IoT) provides unprecedented benefits including optimizing yield, minimizing environmental impact, and reducing cost. However, the mass collection of farm data in IoT applications raises serious concerns about potential privacy leakage that may harm the farmers’ welfare. In this work, we propose a novel scalable and private geo-distance evaluation system, called SPRIDE, to allow application servers to provide geographic-based services by computing the distances among sensors and farms privately. The servers determine the distances without learning any additional information about their locations. The key idea of SPRIDE is to perform efficient distance measurement and distance comparison on encrypted locations over a sphere by leveraging a homomorphic cryptosystem. To serve a large user base, we further propose SPRIDE+ with novel and practical performance enhancements based on pre-computation of cryptographic elements. Through extensive experiments using real-world datasets, we show SPRIDE+ achieves private distance evaluation on a large network of farms, attaining 3+ times runtime performance improvement over existing techniques. We further show SPRIDE+ can run on resource-constrained mobile devices, which offers a practical solution for privacy-preserving precision agriculture IoT applications.

Audio adversarial examples, imperceptible to humans, have been constructed to attack automatic speech recognition (ASR) systems. However, the adversarial examples generated by existing approaches usually incorporate noticeable noises, especially during the periods of silences and pauses. Moreover, the added noises often break temporal dependency property of the original audio, which can be easily detected by state-of-the-art defense mechanisms. In this paper, we propose a new Iterative Proportional Clipping (IPC) algorithm that preserves temporal dependency in audios for generating more robust adversarial examples. We are motivated by an observation that the temporal dependency in audios imposes a significant effect on human perception. Following our observation, we leverage a proportional clipping strategy to reduce noise during the low-intensity periods. Experimental results and user study both suggest that the generated adversarial examples can significantly reduce human-perceptible noises and resist the defenses based on the temporal structure.

Non-orthogonal multiple access (NOMA) has emerged as a new multiple access paradigm for wireless networks. Although many results have been produced for NOMA, most of them are limited to theoretical exploration and performance analysis in cellular networks. Very limited progress has been made so far in the design of practical NOMA schemes for wireless local area networks (WLANs). In this paper, we propose a practical downlink NOMA scheme for WLANs and evaluate its performance in real-world wireless environments. Our NOMA scheme has three key components: precoder design, user grouping, and successive interference cancellation (SIC). On the transmitter side, we first formulate the precoding design problem as an optimization problem and then devise an efficient algorithm to construct precoders for downlink NOMA transmissions. We further propose a lightweight user grouping algorithm to ensure the success of SIC at the receivers. On the receiver side, we propose a new SIC method to decode the desired signal in the presence of strong interference. In contrast to existing SIC methods, our SIC method does not require channel estimation to decode the signals, thereby improving its resilience to interference. We have built a prototype of the proposed NOMA scheme on a wireless testbed. Experimental results show that, compared to orthogonal multiple access (OMA), the proposed NOMA scheme can significantly improve the weak user's date rate (93% on average) and considerably improve WLAN's weighted sum rate (36% on average).

Android inter-app communication (IAC) allows apps to request functionalities from other apps, which has been extensively used to provide a better user experience. However, IAC has also become an enticing target by attackers to launch malicious activities. Dynamic class loading (DCL) and reflection are effective features to enhance the functionality of the apps. In this paper, we expose a new attack that leverages these features in conjunction with inter-app communication to conceal malicious attacks with the ability to bypass existing security mechanisms. To counteract such attack, we present DINA, a novel hybrid analysis approach for identifying malicious IAC behaviors concealed within dynamically loaded code through reflective/DCL calls. DINA appends reflection and DCL invocations to control-flow graphs and continuously performs incremental dynamic analysis to detect the misuse of reflection and DCL that obfuscates malicious Intent communications. DINA utilizes string analysis and inter-procedural analysis to resolve hidden IAC and achieves superior detection performance. Our extensive evaluation on 49,000 real-world apps corroborates the prevalent usage of reflection and DCL, and reveals previously unknown and potentially harmful, hidden IAC behaviors in real-world apps.

Network traffic analysis has been widely used for detecting malware at a large-scale network. Nevertheless, the emerging malware variants and zero-day exploits keep posing significant challenges to malware detection systems. In this paper, we propose DART, a framework for detecting malicious network traffic based on Adaptation Regularization Transfer Learning (ARTL), which effectively copes with the unseen malware variants problem. Specifically, DART trains the adaptive classifier by simultaneously optimizing three factors: (i) the structural risk functions; (ii) the joint distribution between the known malware and unseen malware variants domains; and (iii) the manifold consistency underlying marginal distribution. In addition, DART also works with encrypted network traffic since it does not leverage information related to the packet content. We assess the effectiveness and efficiency of our proposal with a thorough set of experiments. DART achieves over 90% F-measure and 91% recall, outperforming conventional traffic classification methods and other state-of-the-art intrusion detection systems.

Fast response time becomes increasingly important for modern web applications (e.g., e-commerce) due to intense competitive pressure. In this paper, we present a new type of Denial of Service (DoS) Attacks in the cloud, MemCA, with the goal of causing performance uncertainty (the long-tail response time problem) of the target n-tier web application while keeping stealthy. MemCA exploits the sharing nature of public cloud computing platforms by co-locating the adversary VMs with the target VMs that host the target web application, and causing intermittent and short-lived cross-resource contentions on the target VMs. We show that these short-lived cross-resource contentions can cause transient performance interferences that lead to large response time fluctuations of the target web application, due to complex resource dependencies in the system. We further model the attack scenario in n-tier systems based on queuing network theory, and analyze cross-tier queue overflow and tail response time amplification under our attacks. Through extensive benchmark experiments in both private and public clouds (e.g., Amazon EC2), we confirm that MemCA can cause significant performance uncertainty of the target n-tier system while keeping stealthy. Specifically, we show that MemCA not only bypasses the cloud elastic scaling mechanisms, but also the state-of-the-art cloud performance interference detection mechanisms.

Java reflection and dynamic class loading (DCL) are effective features for enhancing the functionalities of Android apps. However, these features can be abused by sophisticated malware to bypass detection schemes. Advanced malware can utilize reflection and DCL in conjunction with Android Inter-App Communication (IAC) to launch collusion attacks using two or more apps. Such dynamically revealed malicious behaviors enable a new type of stealthy, collusive attacks, bypassing all existing detection mechanisms. In this paper, we present DINA, a novel hybrid analysis approach for identifying malicious IAC behaviors concealed within dynamically loaded code through reflective/DCL calls. DINA continuously appends reflection and DCL invocations to control-flow graphs; it then performs incremental dynamic analysis on such augmented graphs to detect the misuse of reflection and DCL that may lead to malicious, yet concealed, IAC activities. Our extensive evaluation on 3,000 real-world Android apps and 14,000 malicious apps corroborates the prevalent usage of reflection and DCL, and reveals previously unknown and potentially harmful, hidden IAC behaviors in real-world apps.

Multiuser MIMO (MU-MIMO) empowers access points (APs) with multiple antennas to transmit multiple data streams concurrently to users by exploiting spatial multiplexing. In MU-MIMO, users need to estimate channel state information (CSI) and report it to APs, thus opening a backdoor to attackers who may forge CSI to eavesdrop the content of victims. In this paper, we explore the eavesdropping attack in a novel and practical context in which CSI forgery entangles MU-MIMO user selection in a many-users regime. The attacker hopes to optimize both the eavesdropping opportunity of being selected with the victim and the corresponding decoding quality. We propose new attack and defense mechanisms: (1) USE Attack that enables attackers to achieve near optimal eavesdropping opportunity and high decoding quality through constructing orthogonal CSI against victims followed by stepwise refinements; (2) AngleSec that exploits channel reciprocity for attacker detection without any modification to legacy CSI feedback in which CSI forgery induces a mismatching of downlink and uplink angular spectra at the AP. We implement and evaluate USE Attack and AngleSec in a software defined radio platform WARPv3. Extensive experiments manifest that USE Attack significantly improves the overall eaves-dropping quality compared with state-of-the-art counterparts and AngleSec is able to detect CSI forgery attackers almost for sure.

Since the performance issues of apps can influence users' experience, developers leverage application performance management (APM) tools to locate the potential performance bottleneck of their apps. Unfortunately, most developers do not understand how APMs monitor their apps during the runtime and whether these APMs have any limitations. In this paper, we demystify APMs by inspecting 25 widely-used APMs that target on Android apps. We first report how these APMs implement 8 key functions as well as their limitations. Then, we conduct a large-scale empirical study on 500,000 Android apps from Google Play to explore the usage of APMs. This study has some interesting observations about existing APMs for Android, including 1) some APMs still use deprecated permissions and approaches so that they may not always work properly; 2) some app developers use APMs to collect users' privacy information.

Energy-saving (ES) systems developed on the basis of the Internet-of-Things (IoT) by heavily relying on automated understanding of human behaviors and activities recognition is of paramount importance in smart home. However, classic approaches are incapable to understand the relations among users' contexts and ES of appliances very well, and they cannot handle massive metering and time-varying user context datasets. Moreover, privacy concern is thoroughly aroused from both the residential and utility provider sides as to its essentiality. To tackle these problems, we propose a privacy-preserving and residential context-aware online ES (PRCOES) system in an IoT-enabled smart home environment. We model the repeated interaction of ES of appliances and the activity recognition of user context as a contextual multiarmed bandits (CMAB) problem, where the context-aware online learning algorithm can predict appropriate energy offers (EOs) that could meet the users' satisfaction, task completion rate, and ES purposes for appliances. We utilize a tree-based structure expanding from top to bottom to recommend EOs, which supports ever-increasing big metering datasets with user context-awareness. Theoretical analysis shows that our proposal achieves sublinear regret and differential privacy for both residents and utility provider. Experiments results validate that PRCOES could enhance users' experience and prolong users' engagement in everyday ES while guarantee the privacy for both residents and utility provider.

In recent years, the scale and diversity of malicious software on mobile networks are constantly increasing, thereby causing considerable danger to users' property and personal privacy. In this study, we devise a method that uses the URLs visited by applications to identify malicious apps. A multi-view neural network is used to create a malware detection model that emphasizes depth and width. This neural network can create multiple views of the input automatically and distribute soft attention weights to focus on different features of input. Multiple views preserve rich semantic information from input for classification without requiring complicated feature engineering. In addition, we conduct comprehensive experiments to compare the proposed method with others and verify the validity of the detection model. The experimental results show that our method has a certain timeliness. It can not only effectively detect malware discovered in different months of a certain year, but also detect potentially malicious apps in the third-party app market. We also compare the detection results of the proposed method on wild apps with 10 popular anti-virus scanners, and the final result shows that our approach ranks second in terms of detection performance.

In wireless LANs (WLANs), network-wide time and frequency synchronization among user devices is widely regarded as a necessity for uplink MU-MIMO. Therefore, to enable uplink MU-MIMO in 802.11ax, dedicated MAC protocols (e.g., trigger frame and timing advance mechanism) have been proposed to synchronize user devices in the time and frequency domains. Such MAC protocols increase not only network complexity but also communication overhead. In this paper, we show that the time and frequency synchronization among user devices is not a necessity for uplink MU-MIMO. We propose a practical uplink MU-MIMO solution which does not require time and frequency alignments of the signals from user devices. The key component in our solution is a new PHY design for AP's receiver, which can decode the concurrent signals from multiple asynchronous user devices. We have built a prototype of our uplink MU-MIMO solution on USPR2-GNURadio testbed. Experimental results show that, using the new PHY, an M-antenna AP can successfully decode the concurrent signals from M asynchronous user devices (2 ≤ M ≤ 4).

In recent years, the number and variety of malicious mobile apps have increased drastically, especially on Android platform, which brings insurmountable challenges for malicious app detection. Researchers endeavor to discover the traces of malicious apps using network traffic analysis. In this study, we combine network traffic analysis with machine learning methods to identify malicious network behavior, and eventually to detect malicious apps. However, most network traffic generated by malicious apps is benign, while only a small portion of traffic is malicious, leading to an imbalanced data problem when the traffic model skews towards modeling the benign traffic. To address this problem, we introduce imbalanced classification methods, including the synthetic minority oversampling technique (SMOTE) + support vector machine (SVM), SVM cost-sensitive (SVMCS), and C4.5 cost-sensitive (C4.5CS) methods. However, when the imbalance rate reaches a certain threshold, the performance of common imbalanced classification algorithms degrades significantly. To avoid performance degradation, we propose to use the imbalanced data gravitation-based classification (IDGC) algorithm to classify imbalanced data. Moreover, we develop a simplex imbalanced data gravitation classification (S-IDGC) model to further reduce the time costs of IDGC without sacrificing the classification performance. In addition, we propose a machine learning based comparative benchmark prototype system, which provides users with substantial autonomy, such as multiple choices of the desired classifiers or traffic features. Using this prototype system, users can compare the detection performance of different classification algorithms on the same data set, as well as the performance of a specific classification algorithm on multiple data sets.

The emergence of malicious apps poses a serious threat to the Android platform. Most types of mobile malware rely on network interface to coordinate operations, steal users' private information, and launch attack activities. In this paper, we propose an effective and automatic malware detection method using the text semantics of network traffic. In particular, we consider each HTTP flow generated by mobile apps as a text document, which can be processed by natural language processing to extract text-level features. Then, we use the text semantic features of network traffic to develop an effective malware detection model. In an evaluation using 31 706 benign flows and 5258 malicious flows, our method outperforms the existing approaches, and gets an accuracy of 99.15%. We also conduct experiments to verify that the method is effective in detecting newly discovered malware, and requires only a few samples to achieve a good detection result. When the detection model is applied to the real environment to detect unknown applications in the wild, the experimental results show that our method performs significantly better than other popular anti-virus scanners with a detection rate of 54.81%. Our method also reveals certain malware types that can avoid the detection of anti-virus scanners. In addition, we design a detection system on encrypted traffic for bring-your-own-device enterprise network, home network, and 3G/4G mobile network. The detection model is integrated into the system to discover suspicious network behaviors.

The alarming growth rate of malicious apps has become a serious issue that sets back the prosperous mobile ecosystem. A recent report indicates that a new malicious app for Android is introduced every 10 s. To combat this serious malware campaign, we need a scalable malware detection approach that can effectively and efficiently identify malware apps. Numerous malware detection tools have been developed, including system-level and network-level approaches. However, scaling the detection for a large bundle of apps remains a challenging task. In this paper, we introduce Significant Permission IDentification (SigPID), a malware detection system based on permission usage analysis to cope with the rapid increase in the number of Android malware. Instead of extracting and analyzing all Android permissions, we develop three levels of pruning by mining the permission data to identify the most significant permissions that can be effective in distinguishing between benign and malicious apps. SigPID then utilizes machine-learning-based classification methods to classify different families of malware and benign apps. Our evaluation finds that only 22 permissions are significant. We then compare the performance of our approach, using only 22 permissions, against a baseline approach that analyzes all permissions. The results indicate that when a support vector machine is used as the classifier, we can achieve over 90% of precision, recall, accuracy, and F-measure, which are about the same as those produced by the baseline approach while incurring the analysis times that are 4-32 times less than those of using all permissions. Compared against other state-of-the-art approaches, SigPID is more effective by detecting 93.62% of malware in the dataset and 91.4% unknown/new malware samples.

Cognitive cellular networks can enable opportunistic network access but their effectiveness relies on adaptive handoff algorithms. However, in cognitive radio networks the usufructuary rights of a secondary user are rescinded due to the unanticipated appearance of a primary user causing potential service disruption. In order to provide uninterrupted service to a cognitive cellular user, we propose elastic handoff as a composite framework of conventional cellular and voluntary spectrum handoffs. As with spectrum handoff, elastic handoff grants secondary users spectrum access while insulating them against the arrival of primary users. On the other hand, it is similar to cellular handoff in providing secondary users service assurance. The setup also offers users multiple network access choices, and affords carriers the means to generate additional revenue by capitalizing on excess capacity. We use a blockchain-based spectrum exchange and smart contracts to implement elastic handoff. Our tests show that user-initiated elastic handoff may reduce call drops by up to half compared to observations from a conventional cellular market, and network-initiated elastic handoff can improve a carrier's revenue maximization prospects.

Cloud-centric cognitive cellular networks utilize dynamic spectrum access and opportunistic network access technologies as a means to mitigate spectrum crunch and network demand. However, furnishing a carrier with personally identifiable information for user setup increases the risk of profiling in cognitive cellular networks, wherein users seek secondary access at various times with multiple carriers. Moreover, network access provisioning - assertion, authentication, authorization, and accounting - implemented in conventional cellular networks is inadequate in the cognitive space, as it is neither spontaneous nor scalable. In this paper, we propose a privacy-enhancing user identity management system using blockchain technology which places due importance on both anonymity and attribution, and supports end-to-end management from user assertion to usage billing. The setup enables network access using pseudonymous identities, hindering the reconstruction of a subscriber's identity. Our test results indicate that this approach diminishes access provisioning duration by up to 4x, decreases network signaling traffic by almost 40%, and enables near real-time user billing that may lead to approximately 3x reduction in payments settlement time.

The growing density of cellular users is placing an unprecedented demand on radio spectrum. Cognitive cellular networks can alleviate spectrum demand through dynamic spectrum access. In order to be fully functional, cellular users not only need spectrum access but also require network access. However, a cellular carrier grants network access only to accredited users. In this paper, we focus on the problem of opportunistic network access for unaccredited users by spontaneous provisioning in the context of cognitive cellular networks. We achieve this for both single and group users by extending the traditional 3A security framework - authentication, authorization, and accounting - to a 5A security paradigm. This entails the addition of network access and user assertion. We design several simulations based on a proof-of-principle prototype to validate our approach against multiple traffic models. The results show our approach can deliver at least 13% improvement in user provisioning time compared to conventional schemes.

Android has become the most popular mobile platform due to its openness and flexibility. Meanwhile, it has also become the main target of massive mobile malware. This phenomenon drives a pressing need for malware detection. In this paper, we propose TrafficAV, which is an effective and explainable detection of mobile malware behavior using network traffic. Network traffic generated by mobile app is mirrored from the wireless access point to the server for data analysis. All data analysis and malware detection are performed on the server side, which consumes minimum resources on mobile devices without affecting the user experience. Due to the difficulty in identifying disparate malicious behaviors of malware from the network traffic, TrafficAV performs a multi-level network traffic analysis, gathering as many features of network traffic as necessary. The proposed method combines network traffic analysis with machine learning algorithm (C4.5 decision tree) that is capable of identifying Android malware with high accuracy. In an evaluation with 8,312 benign apps and 5,560 malware samples, TCP flow detection model and HTTP detection model all perform well and achieve detection rates of 98.16% and 99.65%, respectively. In addition, for the benefit of user, TrafficAV not only displays the final detection results, but also analyzes the behind-the-curtain reason of malicious results. This allows users to further investigate each feature's contribution in the final result, and to grasp the insights behind the final decision.

Jamming attack is a serious threat to the wireless communications. Reactive jamming maximizes the attack efficiency by jamming only when the targets are communicating, which can be readily implemented using software-defined radios. In this paper, we explore the use of the multi-input multi-output (MIMO) technology to achieve jamming resilient orthogonal frequency-division multiplexing (OFDM) communication. In particular, MIMO interference cancellation treats jamming signals as noise and strategically cancels them out, while transmit precoding adjusts the signal directions to optimize the decoding performance. We first investigate the reactive jamming strategies and their impacts on the MIMO-OFDM receivers. We then present a MIMO-based anti-jamming scheme that exploits MIMO interference cancellation and transmit precoding technologies to turn a jammed non-connectivity scenario into an operational network. We implement our jamming resilient communication scheme using software-defined radios. Our testbed evaluation shows the destructive power of reactive jamming attack, and also validates the efficacy and efficiency of our defense mechanisms in the presence of numerous types of reactive jammers with different jamming signal powers.

Advanced botnets adopt a peer-to-peer (P2P) infrastructure for more resilient command and control (C&C). Traditional detection techniques become less effective in identifying bots that communicate via a P2P structure. In this paper, we present PeerClean, a novel system that detects P2P botnets in real time using only high-level features extracted from C&C network flow traffic. PeerClean reliably distinguishes P2P bot-infected hosts from legitimate P2P hosts by jointly considering flow-level traffic statistics and network connection patterns. Instead of working on individual connections or hosts, PeerClean clusters hosts with similar flow traffic statistics into groups. It then extracts the collective and dynamic connection patterns of each group by leveraging a novel dynamic group behavior analysis. Comparing with the individual host-level connection patterns, the collective group patterns are more robust and differentiable. Multi-class classification models are then used to identify different types of bots based on the established patterns. To increase the detection probability, we further propose to train the model with average group behavior, but to explore the extreme group behavior for the detection. We evaluate PeerClean on real-world flow records from a campus network. Our evaluation shows that PeerClean is able to achieve high detection rates with few false positives.

Reactive jamming is considered the most powerful jamming attack as the attack efficiency is maximized while the risk of being detected is minimized. Currently, there are no effective anti-jamming solutions to secure OFDM wireless communications under reactive jamming attack. On the other hand, MIMO has emerged as a technology of great research interest in recent years mostly due to its capacity gain. In this paper, we explore the use of MIMO technology for jamming resilient OFDM communication, especially its capability to communicate against the powerful reactive jammer. We first investigate the jamming strategies and their impacts on the OFDM-MIMO receivers. We then present a MIMO-based anti-jamming scheme that exploits interference cancellation and transmit precoding capabilities of MIMO technology to turn a jammed non-connectivity scenario into an operational network. Our testbed evaluation shows the destructive power of reactive jamming attack, and also validates the efficacy and efficiency of our defense mechanisms.

Passive monitoring by distributed wireless sniffers has been used to strategically capture the network traffic, as the basis of automatic network diagnosis. However, the traditional monitoring techniques fall short in cognitive radio networks (CRNs) due to the much larger number of channels to be monitored and the secondary users' channel availability uncertainty imposed by primary user activities. To better serve CRNs, we propose a systematic passive monitoring framework, i.e., SpecMonitor, for traffic collection using a limited number of sniffers in Wi-Fi-like CRNs. We jointly consider primary user activity and secondary user channel access pattern to optimize the traffic capturing strategy. In particular, we exploit a nonparametric density estimation method to learn and predict secondary users' access pattern in an online fashion, which rapidly adapts to the users' dynamic behaviors and supports accurate estimation of merged access patterns from multiple users. We also design near-optimal monitoring algorithms that maximize two levels of quality-of-monitoring goals based on the predicted channel access patterns. The simulations and experiments show that SpecMonitor outperforms the existing schemes significantly.

In this paper, we propose a privacy-preserving proximity-based security strategy for location-based services in wireless networks, without requiring any pre-shared secret, trusted authority or public key infrastructure. More specifically, radio clients build their location tags according to the unique physical features of their ambient radio signals, which cannot be forged by attackers outside the proximity range. The proximity-based authentication and session key generation is based on the public location tag, which incorporates the received signal strength indicator (RSSI), sequence number and MAC address of the ambient radio packets. Meanwhile, as the basis for the session key generation, the secret location tag consisting of the arrival time interval of the ambient packets, is never broadcast, making it robust against eavesdroppers and spoofers. The proximity test utilizes the nonparametric Bayesian method called infinite Gaussian mixture model, and provides range control by selecting different features of various ambient radio sources. The authentication accuracy and key generation rate are evaluated via experiments using laptops in typical indoor environments.

Passive monitoring by distributed wireless sniffers has been used to strategically capture the network traffic, as the basis of automatic network diagnosis. However, the traditional monitoring techniques fall short in cognitive radio networks (CRNs) due to the much larger number of channels to be monitored, and the secondary users' channel availability uncertainty imposed by primary user activities. To better serve CRNs, we propose a systematic passive monitoring framework for traffic collection using a limited number of sniffers in WiFi like CRNs. We jointly consider primary user activity and secondary user channel access pattern to optimize the traffic capturing strategy. In particular, we exploit a non-parametric density estimation method to learn and predict secondary users' access pattern in an online fashion, which rapidly adapts to the users' dynamic behaviors and supports accurate estimation of merged access patterns from multiple users. We also design near-optimal monitoring algorithms that maximize two levels of quality-of-monitoring goals respectively, based on the predicted channel access patterns. The simulations and experiments show that our proposed framework outperforms the existing schemes significantly.

In this paper, we propose a privacy-preserving proximity-based security system for location-based services in wireless networks, without requiring any pre-shared secret, trusted authority, or public key infrastructure. In this system, the proximity-based authentication and session key establishment are implemented based on spatial temporal location tags. Incorporating the unique physical features of the signals sent from multiple ambient radio sources, the location tags cannot be easily forged by attackers. More specifically, each radio client builds a public location tag according to the received signal strength indicators, sequence numbers, and media access control (MAC) addresses of the ambient packets. Each client also keeps a secret location tag that consists of the packet arrival time information to generate the session keys. As clients never disclose their secret location tags, this system is robust against eavesdroppers and spoofers outside the proximity range. The system improves the authentication accuracy by introducing a nonparametric Bayesian method called infinite Gaussian mixture model in the proximity test and provides flexible proximity range control by taking into account multiple physical-layer features of various ambient radio sources. Moreover, the session key establishment strategy significantly increases the key generation rate by exploiting the packet arrival time of the ambient signals. The authentication accuracy and key generation rate are evaluated via experiments using laptops in typical indoor environments.

Cooperative spectrum sensing is key to the success of cognitive radio networks. Recently, fully distributed cooperative spectrum sensing has been proposed for its high performance benefits particularly in cognitive radio ad hoc networks. However, the cooperative and fully distributed natures of such protocol make it highly vulnerable to malicious attacks, and make the defense very difficult. In this paper, we analyze the vulnerabilities of distributed sensing architecture based on a representative distributed consensus-based spectrum sensing algorithm. We find that such distributed algorithm is particularly vulnerable to a novel form of attack called covert adaptive data injection attack. The vulnerabilities are even magnified under multiple colluding attackers. We further propose effective protection mechanisms, which include a robust distributed outlier detection scheme with adaptive local threshold to thwart the covert adaptive data injection attack, and a hash-based computation verification approach to cope with collusion attacks. Through simulation and analysis, we demonstrate the destructive power of the attacks, and validate the efficacy and efficiency of our proposed protection mechanisms.

This paper presents a theoretical study of the throughput of mobile content distribution (MCD) in vehicular ad hoc networks (VANETs). Since VANET is well-known for its fast-changing topology and adverse wireless channel environments, various protocols have been proposed in the literature to enhance the performance of MCD in a vehicular environment, using packet-level network coding (PLNC) and symbol-level network coding (SLNC). However, there still lacks a fundamental understanding of the limits of MCD protocols using network coding in VANETs. In this paper, we develop a theoretical model to compute the achievable throughput of cooperative MCD in VANETs using SLNC. By considering a one-dimensional road topology with an access point (AP) as the content source, the expected achievable throughput for a vehicle at a certain distance from the AP is derived, for both using PLNC and SLNC. Our proposed model is unique since it captures the effects of multiple practical factors, including vehicle distribution and mobility pattern, channel fading and packet collisions. Through numerical results, we provide insights on optimized design choices for network coding-based cooperative MCD systems in VANETs.