Biblio

The term "artificial intelligence" is a buzzword today and is heavily used to market products, services, research, conferences, and more. It is scientifically disputed which types of products and services do actually qualify as "artificial intelligence" versus simply advanced computer technologies mimicking aspects of natural intelligence. Yet it is undisputed that, despite often inflationary use of the term, there are mainstream products and services today that for decades were only thought to be science fiction. They range from industrial automation, to self-driving cars, robotics, and consumer electronics for smart homes, workspaces, education, and many more contexts. Several technological advances enable what is commonly referred to as "artificial intelligence". It includes connected computers and the Internet of Things (IoT), open and big data, low cost computing and storage, and many more. Yet regardless of the definition of the term artificial intelligence, technological advancements in this area provide immense potential, especially for people with disabilities. In this paper we explore some of these potential in the context of web accessibility. We review some existing products and services, and their support for web accessibility. We propose accessibility conformance evaluation as one potential way forward, to accelerate the uptake of artificial intelligence, to improve web accessibility.

We provide a systemization of knowledge of the recent progress made in addressing the crucial problem of deep learning on encrypted data. The problem is important due to the prevalence of deep learning models across various applications, and privacy concerns over the exposure of deep learning IP and user's data. Our focus is on provably secure methodologies that rely on cryptographic primitives and not trusted third parties/platforms. Computational intensity of the learning models, together with the complexity of realization of the cryptography algorithms hinder the practical implementation a challenge. We provide a summary of the state-of-the-art, comparison of the existing solutions, as well as future challenges and opportunities.

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.

Human behavior is increasingly sensed and recorded and used to create models that accurately predict the behavior of consumers, employees, and citizens. While behavioral models are important in many domains, the ability to predict individuals' behavior is in the focus of growing privacy concerns. The legal and technological measures for privacy do not adequately recognize and address the ability to infer behavior and traits. In this position paper, we first analyze the shortcoming of existing privacy theories in addressing AI's inferential abilities. We then point to legal and theoretical frameworks that can adequately describe the potential of AI to negatively affect people's privacy. We then present a technical privacy measure that can help bridge the divide between legal and technical thinking with respect to AI and privacy.

As a new research hotspot in the field of artificial intelligence, deep reinforcement learning (DRL) has achieved certain success in various fields such as robot control, computer vision, natural language processing and so on. At the same time, the possibility of its application being attacked and whether it have a strong resistance to strike has also become a hot topic in recent years. Therefore, we select the representative Deep Q Network (DQN) algorithm in deep reinforcement learning, and use the robotic automatic pathfinding application as a countermeasure application scenario for the first time, and attack DQN algorithm against the vulnerability of the adversarial samples. In this paper, we first use DQN to find the optimal path, and analyze the rules of DQN pathfinding. Then, we propose a method that can effectively find vulnerable points towards White-Box Q table variation in DQN pathfinding training. Finally, we build a simulation environment as a basic experimental platform to test our method, through multiple experiments, we can successfully find the adversarial examples and the experimental results show that the supervised method we proposed is effective.

The current AI revolution provides us with many new, but often very complex algorithmic systems. This complexity does not only limit understanding, but also acceptance of e.g. deep learning methods. In recent years, explainable AI (XAI) has been proposed as a remedy. However, this research is rarely supported by publications on explanations from social sciences. We suggest a bottom-up approach to explanations for (game) AI, by starting from a baseline definition of understandability informed by the concept of limited human working memory. We detail our approach and demonstrate its application to two games from the GVGAI framework. Finally, we discuss our vision of how additional concepts from social sciences can be integrated into our proposed approach and how the results can be generalised.

To date, numerous ways have been created to learn a fusion solution from data. However, a gap exists in terms of understanding the quality of what was learned and how trustworthy the fusion is for future-i.e., new-data. In part, the current paper is driven by the demand for so-called explainable AI (XAI). Herein, we discuss methods for XAI of the Choquet integral (ChI), a parametric nonlinear aggregation function. Specifically, we review existing indices, and we introduce new data-centric XAI tools. These various XAI-ChI methods are explored in the context of fusing a set of heterogeneous deep convolutional neural networks for remote sensing.

The growing prevalence of cyber threats in the world are affecting every network user. Numerous security monitoring systems are being employed to protect computer networks and resources from falling victim to cyber-attacks. There is a pressing need to have an efficient security monitoring system to monitor the large network datasets generated in this process. A large network datasets representing Malware attacks have been used in this work to establish an expert system. The characteristics of attacker's IP addresses can be extracted from our integrated datasets to generate statistical data. The cyber security expert provides to the weight of each attribute and forms a scoring system by annotating the log history. We adopted a special semi supervise method to classify cyber security log into attack, unsure and no attack by first breaking the data into 3 cluster using Fuzzy K mean (FKM), then manually label a small data (Analyst Intuition) and finally train the neural network classifier multilayer perceptron (MLP) base on the manually labelled data. By doing so, our results is very encouraging as compare to finding anomaly in a cyber security log, which generally results in creating huge amount of false detection. The method of including Artificial Intelligence (AI) and Analyst Intuition (AI) is also known as AI2. The classification results are encouraging in segregating the types of attacks.

Enabled by artificial intelligence techniques, we are witnessing the rise of a new paradigm of computational creativity support: mixed-initiative creative interfaces put human and computer in a tight interactive loop where each suggests, produces, evaluates, modifies, and selects creative outputs in response to the other. This paradigm could broaden and amplify creative capacity for all, but has so far remained mostly confined to artificial intelligence for game content generation, and faces many unsolved interaction design challenges. This workshop therefore convenes CHI and game researchers to advance mixed-initiative approaches to creativity support.

Emerging computing relies heavily on secure backend storage for the massive size of big data originating from the Internet of Things (IoT) smart devices to the Cloud-hosted web applications. Structured Query Language (SQL) Injection Attack (SQLIA) remains an intruder's exploit of choice to pilfer confidential data from the back-end database with damaging ramifications. The existing approaches were all before the new emerging computing in the context of the Internet big data mining and as such will lack the ability to cope with new signatures concealed in a large volume of web requests over time. Also, these existing approaches were strings lookup approaches aimed at on-premise application domain boundary, not applicable to roaming Cloud-hosted services' edge Software-Defined Network (SDN) to application endpoints with large web request hits. Using a Machine Learning (ML) approach provides scalable big data mining for SQLIA detection and prevention. Unfortunately, the absence of corpus to train a classifier is an issue well known in SQLIA research in applying Artificial Intelligence (AI) techniques. This paper presents an application context pattern-driven corpus to train a supervised learning model. The model is trained with ML algorithms of Two-Class Support Vector Machine (TC SVM) and Two-Class Logistic Regression (TC LR) implemented on Microsoft Azure Machine Learning (MAML) studio to mitigate SQLIA. This scheme presented here, then forms the subject of the empirical evaluation in Receiver Operating Characteristic (ROC) curve.

Location-Based Service (LBS) becomes increasingly important for our daily life. However, the localization information in the air is vulnerable to various attacks, which result in serious privacy concerns. To overcome this problem, we formulate a multi-objective optimization problem with considering both the query probability and the practical dummy location region. A low complexity dummy location selection scheme is proposed. We first find several candidate dummy locations with similar query probabilities. Among these selected candidates, a cloaking area based algorithm is then offered to find K - 1 dummy locations to achieve K-anonymity. The intersected area between two dummy locations is also derived to assist to determine the total cloaking area. Security analysis verifies the effectiveness of our scheme against the passive and active adversaries. Compared with other methods, simulation results show that the proposed dummy location scheme can improve the privacy level and enlarge the cloaking area simultaneously.

We are currently witnessing the development of increasingly effective author identification systems (AISs) that have the potential to track users across the internet based on their writing style. In this paper, we discuss two methods for providing user anonymity with respect to writing style: Adversarial Stylometry and Adversarial Authorship. With Adversarial Stylometry, a user attempts to obfuscate their writing style by consciously altering it. With Adversarial Authorship, a user can select an author cluster target (ACT) and write toward this target with the intention of subverting an AIS so that the user's writing sample will be misclassified Our results show that Adversarial Authorship via interactive evolutionary hill-climbing outperforms Adversarial Stylometry.

Information flow security has been considered as a critical requirement on complicated component-based software. The recent efforts on the compositional information flow analyses were limited on the expressiveness of security lattice and the efficiency of compositional enforcement. Extending these approaches to support more general security lattices is usually nontrivial because the compositionality of information flow security properties should be properly treated. In this work, we present a new extension of interface automaton. On this interface structure, we propose two refinement-based security properties, adaptable to any finite security lattice. For each property, we present and prove the security condition that ensures the property to be preserved under composition. Furthermore, we implement the refinement algorithms and the security condition decision procedure. We demonstrate the usability and efficiency of our approach with in-depth case studies. The evaluation results show that our compositional enforcement can effectively reduce the verification cost compared with global verification on composite system.

Undeterred by numerous efforts deployed by antivirus software that shields users from various security threats, ransomware is constantly evolving as technology advances. The impact includes hackers hindering the user's accessibility to their data, and the user will pay ransom to retrieve their data. Ransomware also targets multimillion-dollar organizations, and it can cause colossal data loss. The organizations could face catastrophic consequences, and business operations could be ceased. This research contributes by spreading awareness of ransomware to alert people to tackle ransomware. The solution of this research is the conceptual development of a browser extension that provides assistance to warn users of plausible dangers while surfing the Internet. It allows the users to surf the web safely. Since the contribution of this research is conceptual, we can assume that technology users will adopt the proposed idea to prevent ransomware attacks on their personal computers once the solution is fully implemented in future research.

Motivated by the need to automatically generate behavior-based security challenges to improve user authentication for web services, we consider the problem of large-scale construction of realistic-looking names to serve as aliases for real individuals. We aim to use these names to construct security challenges, where users are asked to identify their real contacts among a presented pool of names. We seek these look-alike names to preserve name characteristics like gender, ethnicity, and popularity, while being unlinkable back to the source individual, thereby making the real contacts not easily guessable by attackers. To achive this, we introduce the technique of distributed name embeddings, representing names in a high-dimensional space such that distance between name components reflects the degree of cultural similarity between these strings. We present different approaches to construct name embeddings from contact lists observed at a large web-mail provider, and evaluate their cultural coherence. We demonstrate that name embeddings strongly encode gender and ethnicity, as well as name popularity. We applied this algorithm to generate imitation names in email contact list challenge. Our controlled user study verified that the proposed technique reduced the attacker's success rate to 26.08%, indistinguishable from random guessing, compared to a success rate of 62.16% from previous name generation algorithms. Finally, we use these embeddings to produce an open synthetic name resource of 1 million names for security applications, constructed to respect both cultural coherence and U.S. census name frequencies.

The purpose of this paper is to analyse the rules of the General Data Protection Regulation on automated decision making in the age of Big Data and to explore how to ensure transparency of such decisions, in particular those taken with the help of algorithms. The GDPR, in its Article 22, prohibits automated individual decision-making, including profiling. On the first impression, it seems that this provision strongly protects individuals and potentially even hampers the future development of AI in decision making. However, it can be argued that this prohibition, containing numerous limitations and exceptions, looks like a Swiss cheese with giant holes in it. Moreover, in case of automated decisions involving personal data of the data subject, the GDPR obliges the controller to provide the data subject with 'meaningful information about the logic involved' (Articles 13 and 14). If we link this information to the rights of data subject, we can see that the information about the logic involved needs to enable him/her to express his/her point of view and to contest the automated decision. While this requirement fits well within the broader framework of GDPR's quest for a high level of transparency, it also raises several queries particularly in cases where the decision is taken with the help of algorithms: What exactly needs to be revealed to the data subject? How can an algorithm-based decision be explained? Apart from technical obstacles, we are facing also intellectual property and state secrecy obstacles to this 'algorithmic transparency'.

Large-scale sensing and actuation infrastructures have allowed buildings to achieve significant energy savings; at the same time, these technologies introduce significant privacy risks that must be addressed. In this paper, we present a framework for modeling the trade-off between improved control performance and increased privacy risks due to occupancy sensing. More specifically, we consider occupancy-based HVAC control as the control objective and the location traces of individual occupants as the private variables. Previous studies have shown that individual location information can be inferred from occupancy measurements. To ensure privacy, we design an architecture that distorts the occupancy data in order to hide individual occupant location information while maintaining HVAC performance. Using mutual information between the individual's location trace and the reported occupancy measurement as a privacy metric, we are able to optimally design a scheme to minimize privacy risk subject to a control performance guarantee. We evaluate our framework using real-world occupancy data: first, we verify that our privacy metric accurately assesses the adversary's ability to infer private variables from the distorted sensor measurements; then, we show that control performance is maintained through simulations of building operations using these distorted occupancy readings.

We present OpenFace, our new open-source face recognition system that approaches state-of-the-art accuracy. Integrating OpenFace with inter-frame tracking, we build RTFace, a mechanism for denaturing video streams that selectively blurs faces according to specified policies at full frame rates. This enables privacy management for live video analytics while providing a secure approach for handling retrospective policy exceptions. Finally, we present a scalable, privacy-aware architecture for large camera networks using RTFace.

As teleoperated robot technology becomes cheaper, more powerful, and more reliable, remotely-operated telepresence robots will become more prevalent in homes and businesses, allowing visitors and business partners to be present without the need to travel. Hindering adoption is the issue of privacy: an Internet-connected telepresence robot has the ability to spy on its local area, either for the remote operator or a third party with access to the video data. Additionally, since the remote operator may move about and manipulate objects without local-user intervention, certain typical privacy-protecting techniques such as moving objects to a different room or putting them in a cabinet may prove insufficient. In this paper, we examine the effects of three whole-image filters on the remote operator's ability to discern details while completing a navigation task.

We consider the problem of privacy-sensitive anomaly detection - screening to detect individuals, behaviors, areas, or data samples of high interest. What defines an anomaly is context-specific; for example, a spoofed rather than genuine user attempting to log in to a web site, a fraudulent credit card transaction, or a suspicious traveler in an airport. The unifying assumption is that the number of anomalous points is quite small with respect to the population, so that deep screening of all individual data points would potentially be time-intensive, costly, and unnecessarily invasive of privacy. Such privacy violations can raise concerns due sensitive nature of data being used, raise fears about violations of data use agreements, and make people uncomfortable with anomaly detection methods. Anomaly detection is well studied, but methods to provide anomaly detection along with privacy are less well studied. Our overall goal in this research is to provide a framework for identifying anomalous data while guaranteeing quantifiable privacy in a rigorous sense. Once identified, such anomalies could warrant further data collection and investigation, depending on the context and relevant policies. In this research, we focus on privacy protection during the deployment of anomaly detection. Our main contribution is a differentially private access mechanism for finding anomalies using a search algorithm based on adaptive noisy group testing. To achieve this, we take as our starting point the notion of group testing [1], which was most famously used to screen US military draftees for syphilis during World War II. In group testing, individuals are tested in groups to limit the number of tests. Using multiple rounds of screenings, a small number of positive individuals can be detected very efficiently. Group testing has the added benefit of providing privacy to individuals through plausible deniability - since the group tests use aggregate data, individual contributions to the test are masked by the group. We follow on these concepts by demonstrating a search model utilizing adaptive queries on aggregated group data. Our work takes the first steps toward strengthening and formalizing these privacy concepts by achieving differential privacy [2]. Differential privacy is a statistical measure of disclosure risk that captures the intuition that an individual's privacy is protected if the results of a computation have at most a very small and quantifiable dependence on that individual's data. In the last decade, there hpractical adoption underway by high-profile companies such as Apple, Google, and Uber. In order to make differential privacy meaningful in the context of a task that seeks to specifically identify some (anomalous) individuals, we introduce the notion of anomaly-restricted differential privacy. Using ideas from information theory, we show that noise can be added to group query results in a way that provides differential privacy for non-anomalous individuals and still enables efficient and accurate detection of the anomalous individuals. Our method ensures that using differentially private aggregation of groups of points, providing privacy to individuals within the group while refining the group selection to the point that we can probabilistically narrow attention to a small numbers of individuals or samples for further attention. To summarize: We introduce a new notion of anomaly-restriction differential privacy, which may be of independent interest. We provide a noisy group-based search algorithm that satisfies the anomaly-restricted differential privacy definition. We provide both theoretical and empirical analysis of our noisy search algorithm, showing that it performs well in some cases, and exhibits the usual privacy/accuracy tradeoff of differentially private mechanisms. Potential anomaly detection applications for our work might include spatial search for outliers: this would rely on new sensing technologies that can perform queries in aggregate to reveal and isolate anomalous outliers. For example, this could lead to privacy-sensitive methods for searching for outlying cell phone activity patterns or Internet activity patterns in a geographic location.

In this paper, we present a differential privacy preserving approach, which extracts personality-based knowledge to serve privacy guarantee data analysis on personal sensitive data. Based on the approach, we further implement an end-to-end privacy guarantee system, KaPPA, to provide researchers iterative data analysis on sensitive data. The key challenge for differential privacy is determining a reasonable amount of privacy budget to balance privacy preserving and data utility. Most of the previous work applies unified privacy budget to all individual data, which leads to insufficient privacy protection for some individuals while over-protecting others. In KaPPA, the proposed personality-based privacy preserving approach automatically calculates privacy budget for each individual. Our experimental evaluations show a significant trade-off of sufficient privacy protection and data utility.

Lately, mobile operators experience threats from SMS grey routes which are used by fraudsters to evade SMS fees and to deny them millions in revenues. But more serious are the threats to the user's security and privacy and consequently the operator's reputation. Therefore, it is crucial for operators to have adequate solutions to protect both their network and their customers against this kind of fraud. Unfortunately, so far there is no sufficiently efficient countermeasure against grey routes. This paper proposes a near real time SMS grey traffic detection which makes use of Counting Bloom Filters combined with blacklist and whitelist to detect SMS grey traffic on the fly and to block them. The proposed detection has been implemented and proved to be quite efficient. The paper provides also comprehensive explanation of SMS grey routes and the challenges in their detection. The implementation and verification are also described thoroughly.

In machine learning, feature engineering has been a pivotal stage in building a high-quality predictor. Particularly, this work explores the multiple Kernel Discriminant Component Analysis (mKDCA) feature-map and its variants. However, seeking the right subset of kernels for mKDCA feature-map can be challenging. Therefore, we consider the problem of kernel selection, and propose an algorithm based on Differential Mutual Information (DMI) and incremental forward search. DMI serves as an effective metric for selecting kernels, as is theoretically supported by mutual information and Fisher's discriminant analysis. On the other hand, incremental forward search plays a role in removing redundancy among kernels. Finally, we illustrate the potential of the method via an application in privacy-aware classification, and show on three mobile-sensing datasets that selecting an effective set of kernels for mKDCA feature-maps can enhance the utility classification performance, while successfully preserve the data privacy. Specifically, the results show that the proposed DMI forward search method can perform better than the state-of-the-art, and, with much smaller computational cost, can perform as well as the optimal, yet computationally expensive, exhaustive search.

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks. To achieve this, we figure out a way to perturb affine transformations of neurons, and loss functions used in deep neural networks. In addition, our mechanism intentionally adds "more noise" into features which are "less relevant" to the model output, and vice-versa. Our theoretical analysis further derives the sensitivities and error bounds of our mechanism. Rigorous experiments conducted on MNIST and CIFAR-10 datasets show that our mechanism is highly effective and outperforms existing solutions.

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and to ensure that no private information about the data is exposed during and after its learning procedure. We utilize a homomorphic cryptosystem that can aggregate the local classifiers while they are encrypted and thus kept secret. To overcome the high computational cost of homomorphic encryption of high-dimensional classifiers, we (1) impose sparsity constraints on local classifier updates and (2) propose a novel efficient encryption scheme named doublypermuted homomorphic encryption (DPHE) which is tailored to sparse high-dimensional data. DPHE (i) decomposes sparse data into its constituent non-zero values and their corresponding support indices, (ii) applies homomorphic encryption only to the non-zero values, and (iii) employs double permutations on the support indices to make them secret. Our experimental evaluation on several public datasets shows that the proposed approach achieves comparable performance against state-of-the-art visual recognition methods while preserving privacy and significantly outperforms other privacy-preserving methods.