1,720,965 research outputs found
A New SVDD Approach to Reliable and Explainable AI
No full textSafety engineering and artificial intelligence are two fields that still need investigation on their reciprocal interactions. Safety should be guaranteed when autonomous decision may lead to risk for the environment and the human. The present work addresses how support vector data description (SVDD) can be redesigned to detect safety regions in a cyber-physical system with zero statistical error. Rule-based knowledge extraction is also presented, to let the SVDD be understandable. Two applications are considered for performance evaluation: domain name server tunneling detection and region of attraction estimation of dynamic systems. Results demonstrate how the new SVDD and its intelligible representation are both suitable in designing safety regions, still maximizing the space of the working conditions
Reliable AI Through SVDD and Rule Extraction
No full textThe proposed paper addresses how Support Vector Data Description (SVDD) can be used to detect safety regions with zero statistical error. It provides a detailed methodology for the applicability of SVDD in real-life applications, such as Vehicle Platooning, by addressing common machine learning problems such as parameter tuning and handling large data sets. Also, intelligible analytics for knowledge extraction with rules is presented: it is targeted to understand safety regions of system parameters. Results are shown by feeding data through simulation to the train of different rule extraction mechanisms
Counterfactual Building and Evaluation via eXplainable Support Vector Data Description
No full textIncreasingly in recent times, the mere prediction of a machine learning algorithm is considered insufficient to gain complete control over the event being predicted. A machine learning algorithm should be considered reliable in the way it allows to extract more knowledge and information than just having a prediction at hand. In this perspective, the counterfactual theory plays a central role. By definition, a counterfactual is the smallest variation of the input such that it changes the predicted behaviour. The paper addresses counterfactuals through Support Vector Data Description (SVDD), empowered by explainability and metric for assessing the counterfactual quality. After showing the specific case in which an analytical solution may be found (under Euclidean distance and linear kernel), an optimisation problem is posed for any type of distances and kernels. The vehicle platooning application is the use case considered to demonstrate how the outlined methodology may offer support to safety-critical applications as well as how explanation may shed new light into the control of the system at hand
Counterfactual Building and Evaluation via eXplainable Support Vector Data Description
Full text linkIncreasingly in recent times, the mere prediction of a machine learning algorithm is considered insufficient to gain complete control over the event being predicted. A machine learning algorithm should be considered reliable in the way it allows to extract more knowledge and information than just having a prediction at hand. In this perspective, the counterfactual theory plays a central role. By definition, a counterfactual is the smallest variation of the input such that it changes the predicted behaviour. The paper addresses counterfactuals through Support Vector Data Description (SVDD), empowered by explainability and metric for assessing the counterfactual quality. After showing the specific case in which an analytical solution may be found (under Euclidean distance and linear kernel), an optimisation problem is posed for any type of distances and kernels. The vehicle platooning application is the use case considered to demonstrate how the outlined methodology may offer support to safety-critical applications as well as how explanation may shed new light into the control of the system at hand
Provably Efficient and Robust Conformal Prediction under a Realistic Threat Model
No full textRobust conformal prediction is a model-agnostic technique designed to construct predictive sets with guaranteed coverage, assuming data exchangeability, even under adversarial attacks. Two primary strategies have been explored to address vulnerabilities to these attacks. The first strategy employs randomization, which is computationally efficient but fails to provide formal performance guarantees without resulting in overly conservative predictive sets. The second strategy involves formal verification, which restores coverage guarantees but leads to excessively conservative predictive sets and prohibitive computational overhead. Indeed, verification generally becomes NP-hard as it attempts to cope with attacks that are practically impossible, rendering some security claims unfalsifiable. In this paper, we propose a novel, provably efficient robust conformal prediction method by clearly defining a realistic threat model. Specifically, we assume explicit knowledge of the set of potential adversarial attacks, aligning our approach with standard certification procedures designed to certify against specific, identified threats. We demonstrate that attacks targeting the model can effectively be reframed as attacks on the score function, allowing us to recalibrate the score quantile to account for these known attacks and thereby restore desired coverage guarantees. It is worth noting that our approach allows to easily incorporate unknown or emerging (zero-day) attacks upon discovery, thus reestablishing coverage guarantees. By avoiding computationally intensive verification and operating under realistic threat assumptions, our approach achieves both efficiency and provable robustness. Empirical evaluations on real-world classification datasets and comparisons with state-of-the-art methods support the effectiveness and practicality of our proposed solution
Structurally stable PWL approximation of nonlinear dynamical systems admitting limit cycles: an example
No full textIn this paper, we propose a variational method to derive the coefficients of piecewise-linear (PWL) models able to accurately approximate nonlinear functions, which are vector fields of autonomous dynamical systems described by continuous-time state-space models dependent on parameters. Such dynamical systems admit limit cycles, and the supercritical Hopf bifurcation normal form is chosen as an example of a system to be approximated. The robustness of the approximations is checked, with a view to circuit implementations
eXplainable and Reliable Against Adversarial Machine Learning in Data Analytics
No full textMachine learning (ML) algorithms are nowadays widely adopted in different contexts to perform autonomous decisions and predictions. Due to the high volume of data shared in the recent years, ML algorithms are more accurate and reliable since training and testing phases are more precise. An important concept to analyze when defining ML algorithms concerns adversarial machine learning attacks. These attacks aim to create manipulated datasets to mislead ML algorithm decisions. In this work, we propose new approaches able to detect and mitigate malicious adversarial machine learning attacks against a ML system. In particular, we investigate the Carlini-Wagner (CW), the fast gradient sign method (FGSM) and the Jacobian based saliency map (JSMA) attacks. The aim of this work is to exploit detection algorithms as countermeasures to these attacks. Initially, we performed some tests by using canonical ML algorithms with a hyperparameters optimization to improve metrics. Then, we adopt original reliable AI algorithms, either based on eXplainable AI (Logic Learning Machine) or Support Vector Data Description (SVDD). The obtained results show how the classical algorithms may fail to identify an adversarial attack, while the reliable AI methodologies are more prone to correctly detect a possible adversarial machine learning attack. The evaluation of the proposed methodology was carried out in terms of good balance between FPR and FNR on real world application datasets: Domain Name System (DNS) tunneling, Vehicle Platooning and Remaining Useful Life (RUL). In addition, a statistical analysis was performed to improve the robustness of the trained models, including evaluating their performance in terms of runtime and memory consumption
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
