Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The term ‘‘Internet-of-Things’’ is used as an umbrella keyword for covering various aspects related to the extension of the Internet and the Web into the physical realm, by means of the widespread deployment of spatially distributed devices with embedded identification, sensing and/or actuation capabilities. Internet-of-Things envisions a future in which digital and physical entities can be linked, by means of appropriate information and communication technologies, to enable a whole new class of applications and services. In this article, we present a survey of technologies, applications and research challenges for Internetof-Things.

/pdf/internet-of-things-vision-applications-and-research-4xfstaiv80.pdf

Internet of things: Vision, applications and research challenges

http://emamispnu.persiangig.com/Projects/Cloud%20Computing/science_2.pdf

Review: A survey on security issues in service delivery models of cloud computing

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform membership inference against a target model, we make adversarial use of machine learning and train our own inference model to recognize differences in the target model's predictions on the inputs that it trained on versus the inputs that it did not train on. We empirically evaluate our inference techniques on classification models trained by commercial "machine learning as a service" providers such as Google and Amazon. Using realistic datasets and classification tasks, including a hospital discharge dataset whose membership is sensitive from the privacy perspective, we show that these models can be vulnerable to membership inference attacks. We then investigate the factors that influence this leakage and evaluate mitigation strategies.

/pdf/membership-inference-attacks-against-machine-learning-models-2tzchejf91.pdf

Membership Inference Attacks Against Machine Learning Models

In this paper, we define and explore proofs of retrievability (PORs). A POR scheme enables an archive or back-up service (prover) to produce a concise proof that a user (verifier) can retrieve a target file F, that is, that the archive retains and reliably transmits file data sufficient for the user to recover F in its entirety.A POR may be viewed as a kind of cryptographic proof of knowledge (POK), but one specially designed to handle a large file (or bitstring) F. We explore POR protocols here in which the communication costs, number of memory accesses for the prover, and storage requirements of the user (verifier) are small parameters essentially independent of the length of F. In addition to proposing new, practical POR constructions, we explore implementation considerations and optimizations that bear on previously explored, related schemes.In a POR, unlike a POK, neither the prover nor the verifier need actually have knowledge of F. PORs give rise to a new and unusual security definition whose formulation is another contribution of our work.We view PORs as an important tool for semi-trusted online archives. Existing cryptographic techniques help users ensure the privacy and integrity of files they retrieve. It is also natural, however, for users to want to verify that archives do not delete or modify files prior to retrieval. The goal of a POR is to accomplish these checks without users having to download the files themselves. A POR can also provide quality-of-service guarantees, i.e., show that a file is retrievable within a certain time bound.

PORs: Proofs of Retrievability for Large Files

Storage outsourcing is a rising trend which prompts a number of interesting security issues, many of which have been extensively investigated in the past. However, Provable Data Possession (PDP) is a topic that has only recently appeared in the research literature. The main issue is how to frequently, efficiently and securely verify that a storage server is faithfully storing its client's (potentially very large) outsourced data. The storage server is assumed to be untrusted in terms of both security and reliability. (In other words, it might maliciously or accidentally erase hosted data; it might also relegate it to slow or off-line storage.) The problem is exacerbated by the client being a small computing device with limited resources. Prior work has addressed this problem using either public key cryptography or requiring the client to outsource its data in encrypted form.In this paper, we construct a highly efficient and provably secure PDP technique based entirely on symmetric key cryptography, while not requiring any bulk encryption. Also, in contrast with its predecessors, our PDP technique allows outsourcing of dynamic data, i.e, it efficiently supports operations, such as block modification, deletion and append.

http://sprout.ics.uci.edu/pubs/a9-ateniese.pdf

Scalable and efficient provable data possession

Machine-learning ML enables computers to learn how to recognise patterns, make unintended decisions, or react to a dynamic environment. The effectiveness of trained machines varies because of more suitable ML algorithms or because superior training sets. Although ML algorithms are known and publicly released, training sets may not be reasonably ascertainable and, indeed, may be guarded as trade secrets. In this paper we focus our attention on ML classifiers and on the statistical information that can be unconsciously or maliciously revealed from them. We show that it is possible to infer unexpected but useful information from ML classifiers. In particular, we build a novel meta-classifier and train it to hack other classifiers, obtaining meaningful information about their training sets. Such information leakage can be exploited, for example, by a vendor to build more effective classifiers or to simply acquire trade secrets from a competitor's apparatus, potentially violating its intellectual property rights.

Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers

A distributed Wireless Sensor Network (WSN) is a collection of n sensors with limited hardware resources. Sensors can exchange messages via Radio Frequency (RF), whose range usually covers only a limited number of other sensors. An interesting problem is how to implement secure pair-wise communications among any pair of sensors in a WSN. A WSN requires completely distributed solutions which are particularly challenging due to the limited resources and the size of the network. Moreover, WSNs can be subject to several security threats, including the physical compromising of a sensor. Hence, any solution for secure pairwise communications should tolerate the collusion of a set of corrupted sensors. This paper describes a probabilistic model and two protocols to establish a secure pair-wise communication channel between any pair of sensors in the WSN, by assigning a small set of random keys to each sensor. We build, based on the first Direct Protocol, a second Co-operative Protocol. The Co-operative Protocol is adaptive: its security properties can be dynamically changed during the life-time of the WSN. Both protocols also guarantee implicit and probabilistic mutual authentication without any additional overhead and without the presence of a base station. The performance of the Direct Protocol is analytically characterized while, for the Co-operative Protocol, we provide both analytical evaluations and extensive simulations. For example, the results show that, assuming each sensor stores 120 keys, in a WSN composed of 1024 sensors with 32 corrupted sensors the probability of a channel corruption is negligible in the case of the Co-operative Protocol.

Random key-assignment for secure Wireless Sensor Networks

Wireless sensor networks are often deployed in hostile environments, where anadversary can physically capture some of the nodes. Once a node is captured, the attackercan re-program it and replicate the node in a large number of clones, thus easily taking over the network. The detection of node replication attacks in a wireless sensor network is therefore a fundamental problem. A few distributed solutions have recently been proposed. However, these solutions are not satisfactory. First, they are energy and memory demanding: A serious drawback for any protocol that is to be used in resource constrained environment such as a sensor network. Further, they are vulnerable to specific adversary models introduced in this paper.The contributions of this work are threefold. First, we analyze the desirable properties of a distributed mechanism for the detection of node replication attacks. Second, we show that the known solutions for this problem do not completely meet our requirements. Third, we propose a new Randomized, Efficient, and Distributed (RED) protocol for the detection of node replication attacks and we show that it is completely satisfactory with respect to the requirements. Extensive simulations also show that our protocol is highly efficient in communication, memory, and computation, that it sets out an improved attack detection probability compared to the best solutions in the literature, and that it is resistant to the new kind of attacks we introduce in this paper, while other solutions are not.

A randomized, efficient, and distributed protocol for the detection of node replication attacks in wireless sensor networks

Mobile devices can be maliciously exploited to violate the privacy of people. In most attack scenarios, the adversary takes the local or remote control of the mobile device, by leveraging a vulnerability of the system, hence sending back the collected information to some remote web service. In this paper, we consider a different adversary, who does not interact actively with the mobile device, but he is able to eavesdrop the network traffic of the device from the network side (e.g., controlling a Wi-Fi access point). The fact that the network traffic is often encrypted makes the attack even more challenging. In this paper, we investigate to what extent such an external attacker can identify the specific actions that a user is performing on her mobile apps. We design a system that achieves this goal using advanced machine learning techniques. We built a complete implementation of this system, and we also run a thorough set of experiments, which show that our attack can achieve accuracy and precision higher than 95%, for most of the considered actions. We compared our solution with the three state-of-the-art algorithms, and confirming that our system outperforms all these direct competitors.

Luigi V. Mancini

Papers

Scalable and efficient provable data possession

Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers

Random key-assignment for secure Wireless Sensor Networks

A randomized, efficient, and distributed protocol for the detection of node replication attacks in wireless sensor networks

Analyzing Android Encrypted Network Traffic to Identify User Actions