1,721,150 research outputs found
Machines We Trust. Perspectives on Dependable AI
No full textArtificial intelligence–based algorithms now marshal an astonishing range of our daily activities, from driving a car (“turn left in 400 yards”) to making a purchase (“products recommended for you”). How can we design AI technologies that humans can trust, especially in such areas of application as law enforcement and the recruitment and hiring process? In this volume, experts from a range of disciplines discuss the ethical and social implications of the proliferation of AI systems, considering bias, transparency, and other issues.
The contributors, offering perspectives from computer science, engineering, law, and philosophy, first lay out the terms of the discussion, considering the “ethical debts” of AI systems, the evolution of the AI field, and the problems of trust and trustworthiness in the context of AI. They go on to discuss specific ethical issues and present case studies of such applications as medicine and robotics, inviting us to shift the focus from the perspective of a “human-centered AI” to that of an “AI-decentered humanity.” Finally, they consider the future of AI, arguing that, as we move toward a hybrid society of cohabiting humans and machines, AI technologies can become humanity's allie
Machines We Trust. Perspectives on Dependable AI
No full textArtificial intelligence–based algorithms now marshal an astonishing range of our daily activities, from driving a car (“turn left in 400 yards”) to making a purchase (“products recommended for you”). How can we design AI technologies that humans can trust, especially in such areas of application as law enforcement and the recruitment and hiring process? In this volume, experts from a range of disciplines discuss the ethical and social implications of the proliferation of AI systems, considering bias, transparency, and other issues.
The contributors, offering perspectives from computer science, engineering, law, and philosophy, first lay out the terms of the discussion, considering the “ethical debts” of AI systems, the evolution of the AI field, and the problems of trust and trustworthiness in the context of AI. They go on to discuss specific ethical issues and present case studies of such applications as medicine and robotics, inviting us to shift the focus from the perspective of a “human-centered AI” to that of an “AI-decentered humanity.” Finally, they consider the future of AI, arguing that, as we move toward a hybrid society of cohabiting humans and machines, AI technologies can become humanity's allie
Multi-feature fusion for image retrieval using constrained dominant sets
No full textAggregating different image features for image retrieval has recently shown its effectiveness. While highly effective, though, the question of how to uplift the impact of the best features for a specific query image persists as an open computer vision problem. in this paper, we propose a computationally efficient approach to fuse several hand-crafted and deep features, based on the probabilistic distribution of a given membership score of a constrained cluster in an unsupervised manner. First, we introduce an incremental nearest neighbor (NN) selection method, whereby we dynamically select k-NN to the query. We then build several graphs from the obtained NN sets and employ constrained dominant sets (CDS) on each graph G to assign edge weights which consider the intrinsic manifold structure of the graph, and detect false matches to the query. Finally, we elaborate the computation of feature positive-impact weight (PIW) based on the dispersive degree of the characteristics vector. To this end, we exploit the entropy of a cluster membership-score distribution. In addition, the final NN set bypasses a heuristic voting scheme. Experiments on several retrieval benchmark datasets show that our method can improve the state-of-the-art result. (C) 2019 Elsevier B.V. All rights reserved
Towards a Generalization of the Motzkin-Straus Theorem to Edge-weighted Graps
No full textRapporto di Ricerca CS - 2002 - 3, Marzo 200
A black-Box adversarial attack for poisoning clustering
Full text linkClustering algorithms play a fundamental role as tools in decision-making and sensible automation pro-cesses. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has become imperative. To the best of our knowledge, however, only a few works have currently addressed this problem. In an attempt to fill this gap, in this work, we propose a black-box adversarial attack for crafting adversarial samples to test the robustness of clustering algo-rithms. We formulate the problem as a constrained minimization program, general in its structure and customizable by the attacker according to her capability constraints. We do not assume any information about the internal structure of the victim clustering algorithm, and we allow the attacker to query it as a service only. In the absence of any derivative information, we perform the optimization with a custom approach inspired by the Abstract Genetic Algorithm (AGA). In the experimental part, we demonstrate the sensibility of different single and ensemble clustering algorithms against our crafted adversarial samples on different scenarios. Furthermore, we perform a comparison of our algorithm with a state-of-the-art approach showing that we are able to reach or even outperform its performance. Finally, to highlight the general nature of the generated noise, we show that our attacks are transferable even against supervised algorithms such as SVMs, random forests and neural networks. (c) 2021 Elsevier Ltd. All rights reserved
A Note on the KKT Points for the Motzkin-Straus Program
Full text linkIn a seminal 1965 paper, Motzkin and Straus established an elegant connection between the clique number of a graph and the global maxima of a quadratic program defined on the standard simplex. Since then, the result has been the subject of intensive research and has served as the motivation for a number of heuristics and bounds for the maximum clique problem. Most of the studies available in the literature, however, focus typically on the local/global solutions of the program, and little or no attention has been devoted so far to the study of its Karush-Kuhn-Tucker (KKT) points. In contrast, in this paper we study the properties of (a parameterized version of) the Motzkin-Straus program and show that its KKT points can provide interesting structural information and are in fact associated with certain regular sub-structures of the underlying graph
A black-Box adversarial attack for poisoning clustering
No full textClustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has become imperative. To the best of our knowledge, however, only a few works have currently addressed this problem. In an attempt to fill this gap, in this work, we propose a black-box adversarial attack for crafting adversarial samples to test the robustness of clustering algorithms. We formulate the problem as a constrained minimization program, general in its structure and customizable by the attacker according to her capability constraints. We do not assume any information about the internal structure of the victim clustering algorithm, and we allow the attacker to query it as a service only. In the absence of any derivative information, we perform the optimization with a custom approach inspired by the Abstract Genetic Algorithm (AGA). In the experimental part, we demonstrate the sensibility of different single and ensemble clustering algorithms against our crafted adversarial samples on different scenarios. Furthermore, we perform a comparison of our algorithm with a state-of-the-art approach showing that we are able to reach or even outperform its performance. Finally, to highlight the general nature of the generated noise, we show that our attacks are transferable even against supervised algorithms such as SVMs, random forests and neural networks
Two metrics for attributed hypergraphs
No full textModern quantitative challenges require to tackle problems on increasingly complex systems in which the relationships between the comprised entities cannot be modelled in a simple pairwise fashion, as graphs do. Such approximation of higher-order relations may lead to a substantial loss of information, hence the need to use more general models than graphs. The most natural choice is to use hypergraphs, discrete structures able to capture k-adic relationships among the entities participating in the problem, modelled as vertices, by grouping them in non-empty sets which constitute the hyperedges of the hypergraph. Since one of the most desirable abilities in this context is to quantify the difference between two such high-order systems, devising distance metrics between hypergraphs becomes of the utmost importance. In this paper, we aim at tackling precisely this problem. Motivated by our previous work on graphs, we propose two distance measures between attributed hypergraphs and we prove that they satisfy the properties of a metric. Both metrics are based on the notion of the maximal common subhypergraph. (c) 2021 Elsevier B.V. All rights reserved
An empirical comparison of node pruning methods for layered feed-forward neural networks
No full textDominant Sets for 'Constrained' Image Segmentation
Full text linkImage segmentation has come a long way since the early days of computer vision, and still remains a challenging task. Modern variations of the classical (purely bottom-up) approach, involve, e.g., some form of user assistance (interactive segmentation) or ask for the simultaneous segmentation of two or more images (co-segmentation). At an abstract level, all these variants can be thought of as constrained versions of the original formulation, whereby the segmentation process is guided by some external source of information. In this paper, we propose a new approach to tackle this kind of problems in a unified way. Our work is based on some properties of a family of quadratic optimization problems related to dominant sets, a graph-theoretic notion of a cluster which generalizes the concept of a maximal clique to edge-weighted graphs. In particular, we show that by properly controlling a regularization parameter which determines the structure and the scale of the underlying problem, we are in a position to extract groups of dominant-set clusters that are constrained to contain predefined elements. In particular, we shall focus on interactive segmentation and co-segmentation (in both the unsupervised and the interactive versions). The proposed algorithm can deal naturally with several types of constraints and input modalities, including scribbles, sloppy contours and bounding boxes, and is able to robustly handle noisy annotations on the part of the user. Experiments on standard benchmark datasets show the effectiveness of our approach as compared to state-of-the-art algorithms on a variety of natural images under several input conditions and constraints
- …
