Among the wide variety of malicious behavior commonly observed in modern social platforms, one of... more Among the wide variety of malicious behavior commonly observed in modern social platforms, one of the most notorious is the diffusion of fake news, given its potential to influence the opinions of millions of people who can be voters, consumers, or simply citizens going about their daily lives. In this paper, we implement and carry out an empirical evaluation of a version of the recently-proposed NetDER architecture for hybrid AI decision-support systems with the capability of leveraging the availability of machine learning modules, logical reasoning about unknown objects, and forecasts based on diffusion processes. NetDER is a general architecture for reasoning about different kinds of malicious behavior such as dissemination of fake news, hate speech, and malware, detection of botnet operations, prevention of cyber attacks including those targeting software products or blockchain transactions, among others. Here, we focus on the case of fake news dissemination on social platforms by three different kinds of users: non-malicious, malicious, and botnet members. In particular, we focus on three tasks: (i) determining who is responsible for posting a fake news article, (ii) detecting malicious users, and (iii) detecting which users belong to a botnet designed to disseminate fake news. Given the difficulty of obtaining adequate data with ground truth, we also develop a testbed that combines real-world fake news datasets with synthetically generated networks of users and fully-detailed traces of their behavior throughout a series of time points. We designed our testbed to be customizable for different problem sizes and settings, and make its code publicly available to be used in similar evaluation efforts. Finally, we report on the results of a thorough experimental evaluation of three variants of our model and six environmental settings over the three tasks. Our results clearly show the effects that the quality of knowledge engineering tasks, the quality of the underlying machine learning classifier used to detect fake news, and the specific environmental conditions have on smart policing efforts in social platforms.Fil: Paredes, José Nicolás. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; ArgentinaFil: Simari, Gerardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; ArgentinaFil: Martinez, Maria Vanina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; ArgentinaFil: Falappa, Marcelo Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentin
X Workshop de Investigadores en Ciencias de la Computación, 2008
En este trabajo presentamos una lí nea de investigación que abarca la de finición de una teoría a... more En este trabajo presentamos una lí nea de investigación que abarca la de finición de una teoría abstracta que captura la dinámica de un marco argumentativo abstracto a través de la aplicación de conceptos de revisión de creencias. Esto comprende dos aportes novedosos: la de finición de un marco argumentativo abstracto dinámico (DAAF, por Dynamic Abstract Argumentation Framework) y la aplicación de conceptos de revisión de creencias sobre el mismo para usufructuar su caracterí stica dinámica. El concepto de dinámica en el ...
IV Congreso Argentina de Ciencias de la Computación, Nov 1, 1998
Belief Revision systems are logical frameworks to modeling the dynamics of knowledge. That is, ho... more Belief Revision systems are logical frameworks to modeling the dynamics of knowledge. That is, how to modify our beliefs when we recieve new information. The main problem arises when the information is inconsistent with beliefs that represents our epistemic state. For instance, suppose we believe that a Ferrari coupe is the fastest car and then, we found that some Porsche car are faster than Ferrari cars. Surely, we need to revise our beliefs in order to accept the new information preserving as much old information as possible. There ...
The entity resolution problem in traditional databases, also known as deduplication, seeks to map... more The entity resolution problem in traditional databases, also known as deduplication, seeks to map multiple virtual objects to its corresponding set of real-world entities. Though the problem is challenging, it can be tackled in a variety of ways by means of leveraging several simplifying assumptions, such as the fact that the multiple virtual objects appear as the result of name or attribute ambiguity, clerical errors in data entry or formatting, missing or changing values, or abbreviations. However, in cyber security domains the entity resolution problem takes on a whole different form, since malicious actors that operate in certain environments like hacker forums and markets are highly motivated to remain semi-anonymous—this is because, though they wish to keep their true identities secret from law enforcement, they also have a reputation with their customers. The above simplifying assumptions cannot be made in this setting, and we therefore coin the term “adversarial deduplicatio...
The Big-5/OCEAN personality traits model, one of the central approaches to psychometrics, has bee... more The Big-5/OCEAN personality traits model, one of the central approaches to psychometrics, has been shown to have many applications over a variety of disciplines. In particular, correlations have been studied leading to effective characterization of people’s behavior, and the model has become notorious for its role in the Cambridge Analytica/Facebook scandal surrounding the 2016 US presidential elections. In this paper, we develop Big-2 (or ROSe, for Relationship to Others and to Self), a model via which the personality of users of online platforms can be studied using a lightweight set of markers focused on online behavior, avoiding the major data privacy pitfalls afflicting approaches based on more powerful models that characterize personal aspects of the human psyche. Evaluation of Big-2’s effectiveness is done in two parts: a quantitative evaluation on a specific prediction task and a qualitative one based on an analysis of the different ways in which the Big-2 traits can be derived from online behavior, proposing a general template to guide such efforts. Quantitative results show that our lightweight model can match or surpass the performance of Big-5 in a prediction task, while qualitative results show that it is feasible to implement the model based on the observation of basic online user behavior. Our main result is a general-purpose model that can be used to characterize the personality traits of users of online platforms in an ethical manner. Our proposed model provides a valuable tool to carry out effective and explainable analyses of online personality, avoiding the collection of unnecessary user data that would open the possibility for ethical violations.
European Conference on Artificial Intelligence, Aug 18, 2014
Over the years, inconsistency management has caught the attention of researchers of different are... more Over the years, inconsistency management has caught the attention of researchers of different areas. Inconsistency is a problem that arises in many different scenarios, for instance, ontology development or knowledge integration. In such settings, it is important to have adequate automatic tools for handling conflicts that may appear in a knowledge base. We introduce an approach to consolidation of belief bases based on a refinement of kernel contraction that accounts for the relation among kernels using clusters instead. We define cluster contraction-based consolidation operators contraction by falsum on a belief base using cluster incision functions, a refinement of kernel incision functions.
Among the wide variety of malicious behavior commonly observed in modern social platforms, one of... more Among the wide variety of malicious behavior commonly observed in modern social platforms, one of the most notorious is the diffusion of fake news, given its potential to influence the opinions of millions of people who can be voters, consumers, or simply citizens going about their daily lives. In this paper, we implement and carry out an empirical evaluation of a version of the recently-proposed NetDER architecture for hybrid AI decision-support systems with the capability of leveraging the availability of machine learning modules, logical reasoning about unknown objects, and forecasts based on diffusion processes. NetDER is a general architecture for reasoning about different kinds of malicious behavior such as dissemination of fake news, hate speech, and malware, detection of botnet operations, prevention of cyber attacks including those targeting software products or blockchain transactions, among others. Here, we focus on the case of fake news dissemination on social platforms by three different kinds of users: non-malicious, malicious, and botnet members. In particular, we focus on three tasks: (i) determining who is responsible for posting a fake news article, (ii) detecting malicious users, and (iii) detecting which users belong to a botnet designed to disseminate fake news. Given the difficulty of obtaining adequate data with ground truth, we also develop a testbed that combines real-world fake news datasets with synthetically generated networks of users and fully-detailed traces of their behavior throughout a series of time points. We designed our testbed to be customizable for different problem sizes and settings, and make its code publicly available to be used in similar evaluation efforts. Finally, we report on the results of a thorough experimental evaluation of three variants of our model and six environmental settings over the three tasks. Our results clearly show the effects that the quality of knowledge engineering tasks, the quality of the underlying machine learning classifier used to detect fake news, and the specific environmental conditions have on smart policing efforts in social platforms.Fil: Paredes, José Nicolás. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; ArgentinaFil: Simari, Gerardo. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; ArgentinaFil: Martinez, Maria Vanina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; ArgentinaFil: Falappa, Marcelo Alejandro. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Bahía Blanca. Instituto de Ciencias e Ingeniería de la Computación. Universidad Nacional del Sur. Departamento de Ciencias e Ingeniería de la Computación. Instituto de Ciencias e Ingeniería de la Computación; Argentin
X Workshop de Investigadores en Ciencias de la Computación, 2008
En este trabajo presentamos una lí nea de investigación que abarca la de finición de una teoría a... more En este trabajo presentamos una lí nea de investigación que abarca la de finición de una teoría abstracta que captura la dinámica de un marco argumentativo abstracto a través de la aplicación de conceptos de revisión de creencias. Esto comprende dos aportes novedosos: la de finición de un marco argumentativo abstracto dinámico (DAAF, por Dynamic Abstract Argumentation Framework) y la aplicación de conceptos de revisión de creencias sobre el mismo para usufructuar su caracterí stica dinámica. El concepto de dinámica en el ...
IV Congreso Argentina de Ciencias de la Computación, Nov 1, 1998
Belief Revision systems are logical frameworks to modeling the dynamics of knowledge. That is, ho... more Belief Revision systems are logical frameworks to modeling the dynamics of knowledge. That is, how to modify our beliefs when we recieve new information. The main problem arises when the information is inconsistent with beliefs that represents our epistemic state. For instance, suppose we believe that a Ferrari coupe is the fastest car and then, we found that some Porsche car are faster than Ferrari cars. Surely, we need to revise our beliefs in order to accept the new information preserving as much old information as possible. There ...
The entity resolution problem in traditional databases, also known as deduplication, seeks to map... more The entity resolution problem in traditional databases, also known as deduplication, seeks to map multiple virtual objects to its corresponding set of real-world entities. Though the problem is challenging, it can be tackled in a variety of ways by means of leveraging several simplifying assumptions, such as the fact that the multiple virtual objects appear as the result of name or attribute ambiguity, clerical errors in data entry or formatting, missing or changing values, or abbreviations. However, in cyber security domains the entity resolution problem takes on a whole different form, since malicious actors that operate in certain environments like hacker forums and markets are highly motivated to remain semi-anonymous—this is because, though they wish to keep their true identities secret from law enforcement, they also have a reputation with their customers. The above simplifying assumptions cannot be made in this setting, and we therefore coin the term “adversarial deduplicatio...
The Big-5/OCEAN personality traits model, one of the central approaches to psychometrics, has bee... more The Big-5/OCEAN personality traits model, one of the central approaches to psychometrics, has been shown to have many applications over a variety of disciplines. In particular, correlations have been studied leading to effective characterization of people’s behavior, and the model has become notorious for its role in the Cambridge Analytica/Facebook scandal surrounding the 2016 US presidential elections. In this paper, we develop Big-2 (or ROSe, for Relationship to Others and to Self), a model via which the personality of users of online platforms can be studied using a lightweight set of markers focused on online behavior, avoiding the major data privacy pitfalls afflicting approaches based on more powerful models that characterize personal aspects of the human psyche. Evaluation of Big-2’s effectiveness is done in two parts: a quantitative evaluation on a specific prediction task and a qualitative one based on an analysis of the different ways in which the Big-2 traits can be derived from online behavior, proposing a general template to guide such efforts. Quantitative results show that our lightweight model can match or surpass the performance of Big-5 in a prediction task, while qualitative results show that it is feasible to implement the model based on the observation of basic online user behavior. Our main result is a general-purpose model that can be used to characterize the personality traits of users of online platforms in an ethical manner. Our proposed model provides a valuable tool to carry out effective and explainable analyses of online personality, avoiding the collection of unnecessary user data that would open the possibility for ethical violations.
European Conference on Artificial Intelligence, Aug 18, 2014
Over the years, inconsistency management has caught the attention of researchers of different are... more Over the years, inconsistency management has caught the attention of researchers of different areas. Inconsistency is a problem that arises in many different scenarios, for instance, ontology development or knowledge integration. In such settings, it is important to have adequate automatic tools for handling conflicts that may appear in a knowledge base. We introduce an approach to consolidation of belief bases based on a refinement of kernel contraction that accounts for the relation among kernels using clusters instead. We define cluster contraction-based consolidation operators contraction by falsum on a belief base using cluster incision functions, a refinement of kernel incision functions.
Uploads
Papers by Marcelo Falappa