Alfredo Milani

Follower

Following

Co-author

Public Views

Uploads

Papers by Alfredo Milani

Enhance while protecting: privacy preserving image filtering

IEEE/WIC/ACM International Conference on Web Intelligence, Dec 14, 2021

Privacy is an important issue raised from the diffusion of deep learning models. These models are... more Privacy is an important issue raised from the diffusion of deep learning models. These models are able to extract unauthorized information from our data, especially from the images shared on Social Networks. In this work we present a nested evolutionary algorithm able to optimize sequences of Instagram-style image filters that, when applied to an image, are able to protect it by fooling classification systems: we turn adversarial attacks into a defence form. Differently from other adversarial techniques adding small perturbations that cannot be easily detected by human eyes but can be easily recognized by softwares, our filter composition cannot be distinguished from any other filter composition used extensively every day to enhance photos and images.

Download

An Efficient Artificial Intelligence Based Technique in Diseases Staging and Forecasting

Journal of Advances in Computer Research, Aug 1, 2013

A Learning Based Approach for Planning with Safe Actions

Lecture Notes in Computer Science, 2020

Given a configuration involving some objects in an environment, the planning problem, considered ... more Given a configuration involving some objects in an environment, the planning problem, considered in this paper, is to find a plan that rearranges these objects so as to place a new object. The challenging aspect here involves deciding when an object can be placed on top of another object. Here only defining standard planning operators would not suffice. For instance, using these operators we can come up with actions that may be performed at a state but it should not be performed. So we introduce the notion of safe actions whose outcomes are consistent with the laws of physics, commonsense, and common practice. A safe action can be performed if a robot performing the action knows the knowledge of the situation. We developed a knowledge engine using a supervised learning technique. However, unlike the common task of learning functions, our approach is to learn predicates–that evaluate to binary values. By learning such a predicate a robot would be able to decide whether or not an object A can be placed on top of another object B. We give a method to handle new objects for which the predicates have not been learned. We suggest a nondeterministic planning algorithm to synthesize plans that contain only safe actions. Experimental results show the efficacy of our approach.

Note di Informatica Umanistica

Preface to ”Evolutionary Computation & Swarm Intelligence”

Mining of Semantic Image Content Using Collective Web Intelligence

Advanced information and knowledge processing, 2010

Human users spend a vast amount of time in interacting with image contents on the Web. Their inte... more Human users spend a vast amount of time in interacting with image contents on the Web. Their interaction entails the exercise of considerable perceptive intelligence, visual judgment and mental evaluation. For high-level semantic image features and concepts, such processes of intelligent judgment cannot be mechanized or carried out automatically by machines. In this chapter, an indexing method is described whereby the aggregate intelligence of different Web users is continuously transferred to the Web. Such intelligence is codified, reinforced, distilled and shared among users so as to enable the systematic mining and discovery of semantic image contents. This method allows the collaborative creation of image indexes, which is able to instill and propagate deep knowledge and collective wisdom into the Web concerning the advanced semantic characteristics of Web images. This method is robust and adaptive, and is able to respond dynamically to changing usage patterns caused by community trends and social networking.

New Trends in AI Planning

Evolutionary Algorithms in Intelligent Systems

Mathematics, Oct 10, 2020

Evolutionary algorithms and metaheuristics are widely used to provide efficient and effective app... more

Download

Defining Classification Ambiguity to Discover a Potential Bias Applied to Emotion Recognition Data Sets

2022 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

Student Behaviour Models for a University LMS

Lecture Notes in Computer Science, 2022

Special Issue “Emerging Artificial Intelligence (AI) Technologies for Learning”

Applied sciences, Sep 1, 2022

Download

Hate Speech and Stereotypes with Artificial Neural Networks

Lecture Notes in Computer Science, 2022

Lie to Me: Shield Your Emotions from Prying Software

Sensors, 2022

Deep learning approaches for facial Emotion Recognition (ER) obtain high accuracy on basic models... more Deep learning approaches for facial Emotion Recognition (ER) obtain high accuracy on basic models, e.g., Ekman’s models, in the specific domain of facial emotional expressions. Thus, facial tracking of users’ emotions could be easily used against the right to privacy or for manipulative purposes. As recent studies have shown that deep learning models are susceptible to adversarial examples (images intentionally modified to fool a machine learning classifier) we propose to use them to preserve users’ privacy against ER. In this paper, we present a technique for generating Emotion Adversarial Attacks (EAAs). EAAs are performed applying well-known image filters inspired from Instagram, and a multi-objective evolutionary algorithm is used to determine the per-image best filters attacking combination. Experimental results on the well-known AffectNet dataset of facial expressions show that our approach successfully attacks emotion classifiers to protect user privacy. On the other hand, th...

Download

A Web-Based System for Emotion Vector Extraction

Computational Science and Its Applications – ICCSA 2017, 2017

The ability of assessing the affective information content is of increasing interest in applicati... more The ability of assessing the affective information content is of increasing interest in applications of computer science, e.g. in human machine interfaces, recommender systems, social robots. In this project, the architecture of a semantic system of emotions is designed and implemented, to quantify the emotional content of short sentences by evaluating and aggregating the semantic proximity of each term in the sentence from the basic emotions defined in a psychological model of emotions (e.g. Ekman, Plutchick, Lovheim). Our model is parametric with respect to the semantic proximity measures, focusing on web-based proximity measures, where data needed to evaluate the proximity can be retrieved from search engines on the Web. To test the performances of the model, a software system has been developed to both collect the statistical data and perform the emotion analysis. The system automatizes the phases of sentence preprocessing, search engine query, results parsing, semantic proximity calculation and the final phase of ranking of emotions.

Download

Knowledge Extraction and Mining in Biomedical Research Using Rule Network Model

Recent findings show that the quantity of published biomedical literature is increasing at a dram... more Recent findings show that the quantity of published biomedical literature is increasing at a dramatic rate. Carrying out knowledge extraction from large amounts of research literature becomes a significant challenge. Here we introduce an automatic mechanism for processing such information and extracting meaningful medical knowledge from biomedical literature. Data mining and natural language processing (NLP) are applied in a novel model, called biomedical rule network model. Using this model, information and relationships among herbal materials and diseases, as well as the chemical constituents of herbs can be extracted automatically. Moreover, with the overlapping chemical constituents of herbs, alternative herbal materials can be discovered, and suggestions can be made to replace expensive treatment options with lower cost ones.

Errors, Biases and Overconfidence in Artificial Emotional Modeling

IEEE/WIC/ACM International Conference on Web Intelligence - Companion Volume, 2019

With the diffusion and successful new implementation of several machine learning techniques, toge... more With the diffusion and successful new implementation of several machine learning techniques, together with the substantial cost decrease of sensors, also included in mobile devices, the field of emotional analysis and modeling has boosted. Apps, web apps, brain-scanning devices, and Artificial Intelligence assistants often include emotion recognition features or emotional behaviors, but new researches contain, maintain, or create several design errors, which analysis is the main aim of this paper.

Neural Network Based Approach for Learning Planning Action Models

Computational Science and Its Applications – ICCSA 2019, 2019

Artificial Intelligence (AI) planning technology represents one of the most efficient solutions t... more Artificial Intelligence (AI) planning technology represents one of the most efficient solutions to guide goal driven agents in domain problems which are mostly characterized by problem solving features. The current proliferation of physical and virtual autonomous agents have therefore triggered a growing interest in the automatic acquisition of action models, which can take advantage of the observation capabilities of agents, which sense world states through their sensors. In this work we present a Neural Network (NN) based approach for learning AI planning action models by observation in noisy environments. The system learns by observing a set of execution patterns of the same action in different contexts. The perceptions of both pre/post action execution states are used to train the NN learning component and are assumed to be affected by noise, which could be due to inaccurate reading or malfunctioning of the sensors. Preliminary experiments shows that the proposed NN learning module seems to be more resilient to unforeseen situations with respect to traditional propositional-based approaches to action model learning.

Emotion Recognition for Self-aid in Addiction Treatment, Psychotherapy, and Nonviolent Communication

Computational Science and Its Applications – ICCSA 2019, 2019

This position paper aims to highlight possible future directions of applications for Affective Co... more This position paper aims to highlight possible future directions of applications for Affective Computing (AC) and Emotion Recognition (ER) for self-aid applications, as they emerge from the experience of the ACER-EMORE Workshops Series. ER in Artificial Intelligence offers a growing number of problem-solving multidisciplinary opportunities. Most current AC and ER applications are focused on a somewhat controversial enterprise-centered approach, i.e., recognizing user emotions to enable a third-party to achieve its own goals, in areas such as e-commerce, cybersecurity, behavior profiling, user experience. In this work we propose to explore a human-centered research direction, aiming at using AC/ER to enhance user consciousness of emotional states, ultimately supporting the development of self-aid applications. The use of facial ER and text ER to help forms of assistive technologies in the fields of Psychotherapy and Communication is an example of such a human-centered approach.

Emotional affordances in human-machine interactive planning and negotiation

Proceedings of the International Conference on Web Intelligence, 2017

Emotional affordances represent a recently introduced concept which model all the mechanisms used... more Emotional affordances represent a recently introduced concept which model all the mechanisms used to collect/transmit emotional meaning in the context of human machine interaction. In this work, we introduce and formally define the cognitive role of emotional affordances in a collaboration human-machine dialogue as tools for triggering or recognizing planning-based activities of delegation, goal negotiation, state acquisition, plan prioritization, taking place with the interaction partner. The presented formal model is grounded in an emergency scenario where reacting to emotional affordances or transmitting an emotional content is instrumental to reach the goal of an effective collaborative response. The implementation issues of generation and recognition of emotional affordance are also discussed.

Social Cooperation in Autonomous Agents to Avoid the Tragedy of the Commons

International Journal of Agricultural and Environmental Information Systems, 2017

In this paper, we address the “Tragedy of the Commons” (TOC) problem for shared-resource systems ... more In this paper, we address the “Tragedy of the Commons” (TOC) problem for shared-resource systems by considering different types of behaviors of agents. On one extreme are self-interested agents while on the other one, agents are concerned about the welfare of the society. Algorithms to capture the different behaviors of the agents with and without interaction among the agents are proposed. An extensive experimental analysis for the different cases has been carried out as well as comparisons of our algorithms with an existing approach. Our study shows that if the agents are willing to sacrifice for some period of time, the sustainability of the society increases considerably.

Download

Alfredo Milani

Uploads

Papers by Alfredo Milani

Log In