Visible to the public Biblio

Found 2371 results

Filters: First Letter Of Last Name is G  [Clear All Filters]
2019-01-31
Tewari, A., Gupta, B. B..  2018.  A Robust Anonymity Preserving Authentication Protocol for IoT Devices. 2018 IEEE International Conference on Consumer Electronics (ICCE). :1–5.

In spite of being a promising technology which will make our lives a lot easier we cannot be oblivious to the fact IoT is not safe from online threat and attacks. Thus, along with the growth of IoT we also need to work on its aspects. Taking into account the limited resources that these devices have it is important that the security mechanisms should also be less complex and do not hinder the actual functionality of the device. In this paper, we propose an ECC based lightweight authentication for IoT devices which deploy RFID tags at the physical layer. ECC is a very efficient public key cryptography mechanism as it provides privacy and security with lesser computation overhead. We also present a security and performance analysis to verify the strength of our proposed approach.

Razaghpanah, Abbas, Niaki, Arian Akhavan, Vallina-Rodriguez, Narseo, Sundaresan, Srikanth, Amann, Johanna, Gill, Philippa.  2018.  Studying TLS Usage in Android Apps. Proceedings of the Applied Networking Research Workshop. :5–5.

First standardized by the IETF in the 1990's, SSL/TLS is the most widely-used encryption protocol on the Internet. This makes it imperative to study its usage across different platforms and applications to ensure proper usage and robustness against attacks and vulnerabilities. While previous efforts have focused on the usage of TLS in the desktop ecosystem, there have been no studies of TLS usage by mobile apps at scale. In our study, we use anonymized data collected by the Lumen mobile measurement app to analyze TLS usage by Android apps in the wild. We analyze and fingerprint handshake messages to characterize the TLS APIs and libraries that apps use, and evaluate their weaknesses. We find that 84% of apps use the default TLS libraries provided by the operating system, and the remaining apps use other TLS libraries for various reasons such as using TLS extensions and features that are not supported by the Android TLS libraries, some of which are also not standardized by the IETF. Our analysis reveals the strengths and weaknesses of each approach, demonstrating that the path to improving TLS security in the mobile platform is not straightforward. Based on work published at: Abbas Razaghpanah, Arian Akhavan Niaki, Narseo Vallina-Rodriguez, Srikanth Sundaresan, Johanna Amann, and Phillipa Gill. 2017. Studying TLS Usage in Android Apps. In Proceedings of CoNEXT '17. ACM, New York, NY, USA, 13 pages. https://doi.org/10.1145/3143361.3143400

Geethanjali, D, Ying, Tan Li, Melissa, Chua Wan Jun, Balachandran, Vivek.  2018.  AEON: Android Encryption Based Obfuscation. Proceedings of the Eighth ACM Conference on Data and Application Security and Privacy. :146–148.

Android applications are vulnerable to reverse engineering which could result in tampering and repackaging of applications. Even though there are many off the shelf obfuscation tools that hardens Android applications, they are limited to basic obfuscation techniques. Obfuscation techniques that transform the code segments drastically are difficult to implement on Android because of the Android runtime verifier which validates the loaded code. In this paper, we introduce a novel obfuscation technique, Android Encryption based Obfuscation (AEON), which can encrypt code segments and perform runtime decryption during execution. The encrypted code is running outside of the normal Android virtual machine, in an embeddable Java source interpreter and thereby circumventing the scrutiny of Android runtime verifier. Our obfuscation technique works well with Android source code and Dalvik bytecode.

Boyle, Elette, Couteau, Geoffroy, Gilboa, Niv, Ishai, Yuval.  2018.  Compressing Vector OLE. Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. :896–912.

Oblivious linear-function evaluation (OLE) is a secure two-party protocol allowing a receiver to learn any linear combination of a pair of field elements held by a sender. OLE serves as a common building block for secure computation of arithmetic circuits, analogously to the role of oblivious transfer (OT) for boolean circuits. A useful extension of OLE is vector OLE (VOLE), allowing the receiver to learn any linear combination of two vectors held by the sender. In several applications of OLE, one can replace a large number of instances of OLE by a smaller number of instances of VOLE. This motivates the goal of amortizing the cost of generating long instances of VOLE. We suggest a new approach for fast generation of pseudo-random instances of VOLE via a deterministic local expansion of a pair of short correlated seeds and no interaction. This provides the first example of compressing a non-trivial and cryptographically useful correlation with good concrete efficiency. Our VOLE generators can be used to enhance the efficiency of a host of cryptographic applications. These include secure arithmetic computation and non-interactive zero-knowledge proofs with reusable preprocessing. Our VOLE generators are based on a novel combination of function secret sharing (FSS) for multi-point functions and linear codes in which decoding is intractable. Their security can be based on variants of the learning parity with noise (LPN) assumption over large fields that resist known attacks. We provide several constructions that offer tradeoffs between different efficiency measures and the underlying intractability assumptions.

Lykou, G., Anagnostopoulou, A., Gritzalis, D..  2018.  Implementing Cyber-Security Measures in Airports to Improve Cyber-Resilience. 2018 Global Internet of Things Summit (GIoTS). :1–6.

Airports are at the forefront of technological innovation, mainly due to the fact that the number of air travel passengers is exponentially increasing every year. As a result, airports enhance infrastructure's intelligence and evolve as smart facilities to support growth, by offering a pleasurable travel experience, which plays a vital role in increasing revenue of aviation sector. New challenges are coming up, which aviation has to deal and adapt, such as the integration of Industrial IoT in airport facilities and the increased use of Bring Your Own Device from travelers and employees. Cybersecurity is becoming a key enabler for safety, which is paramount in the aviation context. Smart airports strive to provide optimal services in a reliable and sustainable manner, by working around the domains of growth, efficiency, safety andsecurity. This paper researches the implementation rate of cybersecurity measures and best practices to improve airports cyber resilience. With the aim to enhance operational practices anddevelop robust cybersecurity governance in smart airports, we analyze security gaps in different areas including technical, organizational practices and policies.

Guri, M., Zadov, B., Daidakulov, A., Elovici, Y..  2018.  xLED: Covert Data Exfiltration from Air-Gapped Networks via Switch and Router LEDs. 2018 16th Annual Conference on Privacy, Security and Trust (PST). :1–12.

An air-gapped network is a type of IT network that is separated from the Internet - physically - due to the sensitive information it stores. Even if such a network is compromised with a malware, the hermetic isolation from the Internet prevents an attacker from leaking out any data - thanks to the lack of connectivity. In this paper we show how attackers can covertly leak sensitive data from air-gapped networks via the row of status LEDs on networking equipment such as LAN switches and routers. Although it is known that some network equipment emanates optical signals correlated with the information being processed by the device (‘side-channel'), malware controlling the status LEDs to carry any type of data (‘covert-channel') has never studied before. Sensitive data can be covertly encoded over the blinking of the LEDs and received by remote cameras and optical sensors. A malicious code is executed in a compromised LAN switch or router allowing the attacker direct, low-level control of the LEDs. We provide the technical background on the internal architecture of switches and routers at both the hardware and software level which enables these attacks. We present different modulation and encoding schemas, along with a transmission protocol. We implement prototypes of the malware and discuss its design and implementation. We tested various receivers including remote cameras, security cameras, smartphone cameras, and optical sensors, and discuss detection and prevention countermeasures. Our experiments show that sensitive data can be covertly leaked via the status LEDs of switches and routers at bit rates of 1 bit/sec to more than 2000 bit/sec per LED.

Rodríguez, Juan M., Merlino, Hernán D., Pesado, Patricia, García-Martínez, Ramón.  2018.  Evaluation of Open Information Extraction Methods Using Reuters-21578 Database. Proceedings of the 2Nd International Conference on Machine Learning and Soft Computing. :87–92.

The following article shows the precision, the recall and the F1-measure for three knowledge extraction methods under Open Information Extraction paradigm. These methods are: ReVerb, OLLIE and ClausIE. For the calculation of these three measures, a representative sample of Reuters-21578 was used; 103 newswire texts were taken randomly from that database. A big discrepancy was observed, after analyzing the obtained results, between the expected and the observed precision for ClausIE. In order to save the observed gap in ClausIE precision, a simple improvement is proposed for the method. Although the correction improved the precision of Clausie, ReVerb turned out to be the most precise method; however ClausIE is the one with the better F1-measure.

Zheng, Erkang, Gates-Idem, Phil, Lavin, Matt.  2018.  Building a Virtually Air-Gapped Secure Environment in AWS: With Principles of Devops Security Program and Secure Software Delivery. Proceedings of the 5th Annual Symposium and Bootcamp on Hot Topics in the Science of Security. :11:1–11:8.

This paper presents the development and configuration of a virtually air-gapped cloud environment in AWS, to secure the production software workloads and patient data (ePHI) and to achieve HIPAA compliance.

Postnikoff, Brittany, Goldberg, Ian.  2018.  Robot Social Engineering: Attacking Human Factors with Non-Human Actors. Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction. :313–314.

Social robots may make use of social abilities such as persuasion, commanding obedience, and lying. Meanwhile, the field of computer security and privacy has shown that these interpersonal skills can be applied by humans to perform social engineering attacks. Social engineering attacks are the deliberate application of manipulative social skills by an individual in an attempt to achieve a goal by convincing others to do or say things that may or may not be in their best interests. In our work we argue that robot social engineering attacks are already possible and that defenses should be developed to protect against these attacks. We do this by defining what a robot social engineer is, outlining how previous research has demonstrated robot social engineering, and discussing the risks that can accompany robot social engineering attacks.

Golbeck, Jennifer.  2018.  Surveillance or Support?: When Personalization Turns Creepy 23rd International Conference on Intelligent User Interfaces. :5–5.

Personalization, recommendations, and user modeling can be powerful tools to improve people's experiences with technology and to help them find information. However, we also know that people underestimate how much of their personal information is used by our technology and they generally do not understand how much algorithms can discover about them. Both privacy and ethical technology have issues of consent at their heart. While many personalization systems assume most users would consent to the way they employ personal data, research shows this is not necessarily the case. This talk will look at how to consider issues of privacy and consent when users cannot explicitly state their preferences, The Creepy Factor, and how to balance users' concerns with the benefits personalized technology can offer.

Menet, Fran\c cois, Berthier, Paul, Gagnon, Michel, Fernandez, José M..  2018.  Spartan Networks: Self-Feature-Squeezing Networks for Increased Robustness in Adversarial Settings. Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security. :2246–2248.

Deep Learning Models are vulnerable to adversarial inputs, samples modified in order to maximize error of the system. We hereby introduce Spartan Networks, Deep Learning models that are inherently more resistant to adverarial examples, without doing any input preprocessing out of the network or adversarial training. These networks have an adversarial layer within the network designed to starve the network of information, using a new activation function to discard data. This layer trains the neural network to filter-out usually-irrelevant parts of its input. These models thus have a slightly lower precision, but report a higher robustness under attack than unprotected models.

2019-01-21
Hasan, S., Ghafouri, A., Dubey, A., Karsai, G., Koutsoukos, X..  2018.  Vulnerability analysis of power systems based on cyber-attack and defense models. 2018 IEEE Power Energy Society Innovative Smart Grid Technologies Conference (ISGT). :1–5.

Reliable operation of power systems is a primary challenge for the system operators. With the advancement in technology and grid automation, power systems are becoming more vulnerable to cyber-attacks. The main goal of adversaries is to take advantage of these vulnerabilities and destabilize the system. This paper describes a game-theoretic approach to attacker / defender modeling in power systems. In our models, the attacker can strategically identify the subset of substations that maximize damage when compromised. However, the defender can identify the critical subset of substations to protect in order to minimize the damage when an attacker launches a cyber-attack. The algorithms for these models are applied to the standard IEEE-14, 39, and 57 bus examples to identify the critical set of substations given an attacker and a defender budget.

Ghafir, Ibrahim, Prenosil, Vaclav, Hammoudeh, Mohammad, Aparicio-Navarro, Francisco J., Rabie, Khaled, Jabban, Ahmad.  2018.  Disguised Executable Files in Spear-phishing Emails: Detecting the Point of Entry in Advanced Persistent Threat. Proceedings of the 2Nd International Conference on Future Networks and Distributed Systems. :44:1–44:5.

In recent years, cyber attacks have caused substantial financial losses and been able to stop fundamental public services. Among the serious attacks, Advanced Persistent Threat (APT) has emerged as a big challenge to the cyber security hitting selected companies and organisations. The main objectives of APT are data exfiltration and intelligence appropriation. As part of the APT life cycle, an attacker creates a Point of Entry (PoE) to the target network. This is usually achieved by installing malware on the targeted machine to leave a back-door open for future access. A common technique employed to breach into the network, which involves the use of social engineering, is the spear phishing email. These phishing emails may contain disguised executable files. This paper presents the disguised executable file detection (DeFD) module, which aims at detecting disguised exe files transferred over the network connections. The detection is based on a comparison between the MIME type of the transferred file and the file name extension. This module was experimentally evaluated and the results show a successful detection of disguised executable files.

Fortes, Reinaldo Silva, Lacerda, Anisio, Freitas, Alan, Bruckner, Carlos, Coelho, Dayanne, Gonçalves, Marcos.  2018.  User-Oriented Objective Prioritization for Meta-Featured Multi-Objective Recommender Systems. Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization. :311–316.

Multi-Objective Recommender Systems (MO-RS) consider several objectives to produce useful recommendations. Besides accuracy, other important quality metrics include novelty and diversity of recommended lists of items. Previous research up to this point focused on naive combinations of objectives. In this paper, we present a new and adaptable strategy for prioritizing objectives focused on users' preferences. Our proposed strategy is based on meta-features, i.e., characteristics of the input data that are influential in the final recommendation. We conducted a series of experiments on three real-world datasets, from which we show that: (i) the use of meta-features leads to the improvement of the Pareto solution set in the search process; (ii) the strategy is effective at making choices according to the specificities of the users' preferences; and (iii) our approach outperforms state-of-the-art methods in MO-RS.

Shen, Sheng, Roy, Nirupam, Guan, Junfeng, Hassanieh, Haitham, Choudhury, Romit Roy.  2018.  MUTE: Bringing IoT to Noise Cancellation. Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication. :282–296.

Active Noise Cancellation (ANC) is a classical area where noise in the environment is canceled by producing anti-noise signals near the human ears (e.g., in Bose's noise cancellation headphones). This paper brings IoT to active noise cancellation by combining wireless communication with acoustics. The core idea is to place an IoT device in the environment that listens to ambient sounds and forwards the sound over its wireless radio. Since wireless signals travel much faster than sound, our ear-device receives the sound in advance of its actual arrival. This serves as a glimpse into the future, that we call lookahead, and proves crucial for real-time noise cancellation, especially for unpredictable, wide-band sounds like music and speech. Using custom IoT hardware, as well as lookahead-aware cancellation algorithms, we demonstrate MUTE, a fully functional noise cancellation prototype that outperforms Bose's latest ANC headphone. Importantly, our design does not need to block the ear - the ear canal remains open, making it comfortable (and healthier) for continuous use.

Sayoud, Akila, Djendi, Mohamed, Guessoum, Abderrezak.  2018.  A Two-Sensor Fast Adaptive Algorithm for Blind Speech Enhancement. Proceedings of the Fourth International Conference on Engineering & MIS 2018. :24:1–24:4.

This paper presents the enhancement of speech signals in a noisy environment by using a Two-Sensor Fast Normalized Least Mean Square adaptive algorithm combined with the backward blind source separation structure. A comparative study with other competitive algorithms shows the superiority of the proposed algorithm in terms of various objective criteria such as the segmental signal to noise ratio (SegSNR), the cepstral distance (CD), the system mismatch (SM) and the segmental mean square error (SegMSE).

Kafash, S. H., Giraldo, J., Murguia, C., Cárdenas, A. A., Ruths, J..  2018.  Constraining Attacker Capabilities Through Actuator Saturation. 2018 Annual American Control Conference (ACC). :986–991.
For LTI control systems, we provide mathematical tools - in terms of Linear Matrix Inequalities - for computing outer ellipsoidal bounds on the reachable sets that attacks can induce in the system when they are subject to the physical limits of the actuators. Next, for a given set of dangerous states, states that (if reached) compromise the integrity or safe operation of the system, we provide tools for designing new artificial limits on the actuators (smaller than their physical bounds) such that the new ellipsoidal bounds (and thus the new reachable sets) are as large as possible (in terms of volume) while guaranteeing that the dangerous states are not reachable. This guarantees that the new bounds cut as little as possible from the original reachable set to minimize the loss of system performance. Computer simulations using a platoon of vehicles are presented to illustrate the performance of our tools.
Murillo, Andrés Felipe, Cómbita, Luis Francisco, Gonzalez, Andrea Calderón, Rueda, Sandra, Cardenas, Alvaro A., Quijano, Nicanor.  2018.  A Virtual Environment for Industrial Control Systems: A Nonlinear Use-Case in Attack Detection, Identification, and Response. Proceedings of the 4th Annual Industrial Control System Security Workshop. :25–32.

The integration of modern information technologies with industrial control systems has created an enormous interest in the security of industrial control, however, given the cost, variety, and industry practices, it is hard for researchers to test and deploy security solutions in real-world systems. Industrial control testbeds can be used as tools to test security solutions before they are deployed, and in this paper we extend our previous work to develop open-source virtual industrial control testbeds where computing and networking components are emulated and virtualized, and the physical system is simulated through differential equations. In particular, we implement a nonlinear control system emulating a three-water tank with the associated sensors, PLCs, and actuators that communicate through an emulated network. In addition, we design unknown input observers (UIO) to not only detect that an attack is occurring, but also to identify the source of the malicious false data injections and mitigate its impact. Our system is available through Github to the academic community.

Selvaraj, Jayaprakash, Dayanıklı, Gökçen Y?lmaz, Gaunkar, Neelam Prabhu, Ware, David, Gerdes, Ryan M., Mina, Mani.  2018.  Electromagnetic Induction Attacks Against Embedded Systems. Proceedings of the 2018 on Asia Conference on Computer and Communications Security. :499–510.

Embedded and cyber-physical systems are critically dependent on the integrity of input and output signals for proper operation. Input signals acquired from sensors are assumed to correspond to the phenomenon the system is monitoring and responding to. Similarly, when such systems issue an actuation signal it is expected that the mechanism being controlled will respond in a predictable manner. Recent work has shown that sensors can be manipulated through the use of intentional electromagnetic interference (IEMI). In this work, we demonstrate thatboth input and output signals, analog and digital, can be remotely manipulated via the physical layer—thus bypassing traditional integrity mechanisms. Through the use of specially crafted IEMI it is shown that the physical layer signaling used for sensor input to, and digital communications between, embedded systems may be undermined to an attacker's advantage. Three attack scenarios are analyzed and their efficacy demonstrated. In the first scenario the analog sensing channel is manipulated to produce arbitrary sensor readings, while in the second it is shown that an attacker may induce bit flips in serial communications. Finally, a commonly used actuation signal is shown to be vulnerable to IEMI. The attacks are effective over appreciable distances and at low power.

Yu, Z., Du, H., Xiao, D., Wang, Z., Han, Q., Guo, B..  2018.  Recognition of Human Computer Operations Based on Keystroke Sensing by Smartphone Microphone. IEEE Internet of Things Journal. 5:1156–1168.

Human computer operations such as writing documents and playing games have become popular in our daily lives. These activities (especially if identified in a non-intrusive manner) can be used to facilitate context-aware services. In this paper, we propose to recognize human computer operations through keystroke sensing with a smartphone. Specifically, we first utilize the microphone embedded in a smartphone to sense the input audio from a computer keyboard. We then identify keystrokes using fingerprint identification techniques. The determined keystrokes are then corrected with a word recognition procedure, which utilizes the relations of adjacent letters in a word. Finally, by fusing both semantic and acoustic features, a classification model is constructed to recognize four typical human computer operations: 1) chatting; 2) coding; 3) writing documents; and 4) playing games. We recruited 15 volunteers to complete these operations, and evaluated the proposed approach from multiple aspects in realistic environments. Experimental results validated the effectiveness of our approach.

Gao, J., Wang, J., Zhang, L., Yu, Q., Huang, Y., Shen, Y..  2019.  Magnetic Signature Analysis for Smart Security System Based on TMR Magnetic Sensor Array. IEEE Sensors Journal. :1–1.

This paper presents a novel low power security system based on magnetic anomaly detection by using Tunneling Magnetoresistance (TMR) magnetic sensors. In this work, a smart light has been developed, which consists of TMR sensors array, detection circuits, a micro-controller and a battery. Taking the advantage of low power consumption of TMR magnetic sensors, the smart light powered by Li-ion battery can work for several months. Power Spectrum Density of the obtained signal was analyzed to reject background noise and improve the signal to noise ratio effectively by 1.3 dB, which represented a 30% detection range improvement. Also, by sending the signals to PC, the magnetic fingerprints of the objects have been configured clearly. In addition, the quick scan measurement has been also performed to demonstrate that the system can discriminate the multiple objects with 30 cm separation. Since the whole system was compact and portable, it can be used for security check at office, meeting room or other private places without attracting any attention. Moreover, it is promising to integrate multiply such systems together to achieve a wireless security network in large-scale monitoring.

Cabaj, Krzysztof, Gregorczyk, Marcin, Mazurczyk, Wojciech, Nowakowski, Piotr, \textbackslashtextbackslash.Zórawski, Piotr.  2018.  SDN-based Mitigation of Scanning Attacks for the 5G Internet of Radio Light System. Proceedings of the 13th International Conference on Availability, Reliability and Security. :49:1–49:10.
Currently 5G communication networks are gaining on importance among industry, academia, and governments worldwide as they are envisioned to offer wide range of high-quality services and unfaltering user experiences. However, certain security, privacy and trust challenges need to be addressed in order for the 5G networks to be widely welcomed and accepted. That is why in this paper, we take a step towards these requirements and we introduce a dedicated SDN-based integrated security framework for the Internet of Radio Light (IoRL) system that is following 5G architecture design. In particular, we present how TCP SYN-based scanning activities which typically comprise the first phase of the attack chain can be detected and mitigated using such an approach. Enclosed experimental results prove that the proposed security framework has potential to become an effective defensive solution.
Saeed, A., Garraghan, P., Craggs, B., Linden, D. v d, Rashid, A., Hussain, S. A..  2018.  A Cross-Virtual Machine Network Channel Attack via Mirroring and TAP Impersonation. 2018 IEEE 11th International Conference on Cloud Computing (CLOUD). :606–613.

Data privacy and security is a leading concern for providers and customers of cloud computing, where Virtual Machines (VMs) can co-reside within the same underlying physical machine. Side channel attacks within multi-tenant virtualized cloud environments are an established problem, where attackers are able to monitor and exfiltrate data from co-resident VMs. Virtualization services have attempted to mitigate such attacks by preventing VM-to-VM interference on shared hardware by providing logical resource isolation between co-located VMs via an internal virtual network. However, such approaches are also insecure, with attackers capable of performing network channel attacks which bypass mitigation strategies using vectors such as ARP Spoofing, TCP/IP steganography, and DNS poisoning. In this paper we identify a new vulnerability within the internal cloud virtual network, showing that through a combination of TAP impersonation and mirroring, a malicious VM can successfully redirect and monitor network traffic of VMs co-located within the same physical machine. We demonstrate the feasibility of this attack in a prominent cloud platform - OpenStack - under various security requirements and system conditions, and propose countermeasures for mitigation.

2019-01-16
Aloui, M., Elbiaze, H., Glitho, R., Yangui, S..  2018.  Analytics as a service architecture for cloud-based CDN: Case of video popularity prediction. 2018 15th IEEE Annual Consumer Communications Networking Conference (CCNC). :1–4.
User Generated Videos (UGV) are the dominating content stored in scattered caches to meet end-user Content Delivery Networks (CDN) requests with quality of service. End-User behaviour leads to a highly variable UGV popularity. This aspect can be exploited to efficiently utilize the limited storage of the caches, and improve the hit ratio of UGVs. In this paper, we propose a new architecture for Data Analytics in Cloud-based CDN to derive UGVs popularity online. This architecture uses RESTful web services to gather CDN logs, store them through generic collections in a NoSQL database, and calculate related popular UGVs in a real time fashion. It uses a dynamic model training and prediction services to provide each CDN with related popular videos to be cached based on the latest trained model. The proposed architecture is implemented with k-means clustering prediction model and the obtained results are 99.8% accurate.
Chen, Muhao, Zhao, Qi, Du, Pengyuan, Zaniolo, Carlo, Gerla, Mario.  2018.  Demand-driven Cache Allocation Based on Context-aware Collaborative Filtering. Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing. :302–303.
Many recent advances of network caching focus on i) more effectively modeling the preferences of a regional user group to different web contents, and ii) reducing the cost of content delivery by storing the most popular contents in regional caches. However, the context under which the users interact with the network system usually causes tremendous variations in a user group's preferences on the contents. To effectively leverage such contextual information for more efficient network caching, we propose a novel mechanism to incorporate context-aware collaborative filtering into demand-driven caching. By differentiating the characterization of user interests based on a priori contexts, our approach seeks to enhance the cache performance with a more dynamic and fine-grained cache allocation process. In particular, our approach is general and adapts to various types of context information. Our evaluation shows that this new approach significantly outperforms previous non-demand-driven caching strategies by offering much higher cached content rate, especially when utilizing the contextual information.