As with other businesses, tourist companies are taking advantage of modern technologies. Chatbots are a recent technology that hotels, travel agencies, and airline companies are adopting. Despite t...

Predicting the intentions to use chatbots for travel and tourism

Chatbots have become the go-to platform for users to receive answers to their queries. They are now being used by many businesses too to provide their customers with a virtual assistant to answer their queries. But when it comes to engaging with a user in a dialogue, existing chatbots have several shortcomings, with issues such as failing to provide a meaningful response to the user, offering semantically incorrect information etc. This paper studies the working styles of existing chatbots in generating a response and then identifies their shortcomings from the viewpoint of engaging in a dialogue with a user. It then proposes a domain-specific chatbot named IntelliBot, which is a response-generating dialogue-based chatbot that uses multiple strategies to generate a response. IntelliBot was trained on two datasets, namely the Cornell movie dialogue and a custom-built insurance dataset so it has domain-specific knowledge. The performance of IntelliBot was then validated and compared with three other chatbots from the literature, namely RootyAI, ChatterBot and DeepQA. The results demonstrate IntelliBot’s superiority in engaging with the user and providing a complete answer in the insurance domain.

IntelliBot: A Dialogue-based chatbot for the insurance industry

Power side-channel attacks, capable of deducing secret using statistical analysis techniques, have become a serious threat to devices in cyber-physical systems and the Internet of things. Random masking is a widely used countermeasure for removing the statistical dependence between secret data and side-channel leaks. Although there are techniques for verifying whether software code has been perfectly masked, they are limited in accuracy and scalability. To bridge this gap, we propose a refinement-based method for verifying masking countermeasures. Our method is more accurate than prior syntactic type inference based approaches and more scalable than prior model-counting based approaches using SAT or SMT solvers. Indeed, it can be viewed as a gradual refinement of a set of semantic type inference rules for reasoning about distribution types. These rules are kept abstract initially to allow fast deduction, and then made concrete when the abstract version is not able to resolve the verification problem. We have implemented our method in a tool and evaluated it on cryptographic benchmarks including AES and MAC-Keccak. The results show that our method significantly outperforms state-of-the-art techniques in terms of both accuracy and scalability.

/pdf/scinfer-refinement-based-verification-of-software-28lljweot2.pdf

SCInfer: Refinement-based verification of software countermeasures against side-channel attacks

Bots are destined to dominate how humans interact with the internet of things that continues to grow around them. Despite their still budding intellectual capacity, major companies (e.g., Apple, Google and Amazon) have already placed (chat)bots at the centre of their flagship devices. (Chat)Bots currently fill the internet acting as guides, merchants and assistants. Chatbots, designed as communicators, however, have yet to make a meaningful contribution to perhaps their most natural vocation: foreign language learning partners. This review engages in three questions that surround this issue: 1. Why are chatbots not already at the centre of foreign language learning? 2. What are two key developers of chatbots working towards that might push chatbots into the language learning spotlight? 3. What might researchers, educators, and developers together do to support chatbots as foreign language learning partners right now?

/pdf/bots-for-language-learning-now-current-and-future-directions-1jm2lejjhw.pdf

Bots for language learning now: Current and future directions

Power side-channel attacks, capable of deducing secret data using statistical analysis, have become a serious threat. Random masking is a widely used countermeasure for removing the statistical dependence between secret data and side-channel information. Although there are techniques for verifying whether a piece of software code is perfectly masked, they are limited in accuracy and scalability. To bridge this gap, we propose a refinement-based method for verifying masking countermeasures. Our method is more accurate than prior type-inference-based approaches and more scalable than prior model-counting-based approaches using SAT or SMT solvers. Indeed, our method can be viewed as a gradual refinement of a set of type-inference rules for reasoning about distribution types. These rules are kept abstract initially to allow fast deduction and then made concrete when the abstract version is not able to resolve the verification problem. We also propose algorithms for quantifying the amount of side-channel information leakage from a software implementation using the notion of quantitative masking strength. We have implemented our method in a software tool and evaluated it on cryptographic benchmarks including AES and MAC-Keccak. The experimental results show that our method significantly outperforms state-of-the-art techniques in terms of accuracy and scalability.

Verifying and Quantifying Side-channel Resistance of Masked Software Implementations

Chatbots, i.e., conversational software agents able to interact with users via instant messaging channels like Messenger, WhatsApp or SMS, have the power to substantively simplify human-computer interaction thanks to their natural language paradigm. While this certainly helps to lower barriers, state-of-the-art chatbots prevalently provide access to generic, non-personalized features with relatively little usefulness. This may hinder adoption. To provide users with real value, we envision a kind of chatbot that is personal and helpful by providing services that are chosen and configured by the users themselves, for themselves. As the development of a one-size-fits-all, yet flexible and customizable bot is hard, if not impossible, we discuss requirements and design options that directly put the user into control of their own personal bot.

/pdf/toward-truly-personal-chatbots-on-the-development-of-custom-52kaaoday5.pdf

Toward truly personal chatbots: on the development of custom conversational assistants

In this paper, we deal with the problem of efficiently assessing the higher order vulnerability of a hardware cryptographic circuit. Our main concern is to provide methods that allow a circuit designer to detect early in the design cycle if the implementation of a Boolean-additive masking countermeasure does not hold up to the required protection order. To achieve this goal, we promote the search for vulnerabilities from a statistical problem to a purely symbolical one and then provide a method for reasoning about this new symbolical interpretation. Eventually we show, with a synthetic example, how the proposed conceptual tool can be used for exploring the vulnerability space of a cryptographic primitive.

Symbolic Analysis of Higher-Order Side Channel Countermeasures

This paper presents a framework for the design of chatbots for data exploration. With respect to conversational virtual assistants (such as Amazon Alexa or Apple Siri), this class of chatbots exploits structured input to retrieve data from known data sources. The approach is based on a conceptual representation of the available data sources, and on a set of modeling abstractions that allow designers to characterize the role that key data elements play in the user requests to be handled. Starting from the resulting specifications, the framework then generates a conversation for exploring the content exposed by the considered data sources.

/pdf/conversational-data-exploration-43y49r28zc.pdf

Conversational Data Exploration

This paper presents a design methodology and an accompanying platform for the design and fast development of Context-Aware Mobile mashUpS (CAMUS). The approach is characterized by the role given to context as a first-class modeling dimension used to support (i) the identification of the most adequate resources that can satisfy the users’ situational needs and (ii) the consequent tailoring at runtime of the provided data and functions. Context-based abstractions are exploited to generate models specifying how data returned by the selected services have to be merged and visualized by means of integrated views. Thanks to the adoption of Model-Driven Engineering (MDE) techniques, these models drive the flexible execution of the final mobile app on target mobile devices. A prototype of the platform, making use of novel and advanced Web and mobile technologies, is also illustrated.

/pdf/on-the-role-of-context-in-the-design-of-mobile-mashups-40p1rkhnwi.pdf

On the Role of Context in the Design of Mobile Mashups

In this work we provide a spectral formalization of non-interference in the presence of glitches. Our goal is to present new theoretical and practical tools to reason about robust-d-probing security. We show that the current understanding of extended probes lends itself to probes that participate, during gadget composition, to the creation of additional extended probes. In turn, this enables a natural extension of non-interference definitions into robust ones to build a new reasoning framework that can formally explain some semi-formal results already appeared in the past and be used to synthesize new robust-d-SNI gadgets.

Vittorio Zaccaria

Papers

Toward truly personal chatbots: on the development of custom conversational assistants

Symbolic Analysis of Higher-Order Side Channel Countermeasures

Conversational Data Exploration

On the Role of Context in the Design of Mobile Mashups

On the spectral features of robust probing security