Spain

ECAI 2020

Black-box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN

malware

generative adversarial networks

adversarial attacks

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


AAAI 2023

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

technical paper

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

Explainable Inference in the FRANK Query Answering System

Algorithms are here to stay. They are transforming the way we live and work and increasingly replace cognitively human ways of making decisions. The so called “algorithmocracy” or the ecosystem that we all now inhabit, where algorithms govern many aspects of our behavior, has the potential to bias and be deployed at large scales. Because the automation of decisions by algorithms promise efficiency and resource maximization, AI technologies can be used to meet the 17 Sustainable Development Goals and its 169 targets. However, we must ensure that its application is humane and ethical and within a normative framework guided by basic ethical principles. Here, we try to clarify what people really mean by “ethics” in AI ethics and elucidate a roadmap to implement “ethics by design” standards to establish satisfactory measures of fairness, transparency and explainability of algorithms when use for social good as for example the promotion of Sustainable Development Goals

AI ethics for Sustainable Development Goals

The Artificial Intelligence (AI) revolution brings unique opportunities to help improve the life of every citizen, but also new threats. AI is transforming not only business and every aspect of our lives but also the social fabric we inhabit, including the governments and public organisations. In this Digital Transformation process, we find that many decision-makers, politicians and public servants feel lost on how to apply AI, how to benefit from data analytics and how to transform to improve not only the existing services but the administration too. In this Digital Transformation process is crucial that administrations take into consideration the ethical dimension of the use of AI in data analytics. Public administrations need a vision of how to integrate AI ethically to guarantee fair and unbiased services for the citizens. In this paper, we explore the AI Digital transformation in public services, the fAIr initiative and introduce a current application to a real case in Jalisco, Mexico. The explosion of AI technologies with connected benefits and risks are at the centre of a global discussion.

To be fAIr or not be. Using AI for the good of citizens.

The alarming trend of increasing mental health problems and the global inability to find effective ways to address them is hampering both individual and societal prosperity. Barriers to access mental health care are many and high, ranging from socio-economic inequalities to personal stigmas. This gives technology, especially technology based in artificial intelligence, the opportunity to help alleviate the situation and offer unique solutions. The multi- and interdisciplinary research on persuasive technology, which attempts to change behavior or attitudes without deception or coercion, shows promise in improving well-being, which results in increased equality. This paper presents such systems with a brief overview of the field, and offers general, technical and critical thoughts on the implementation as well as impact. We believe that such technology can complement existing mental health care solutions to reduce inequalities in access as well as inequalities resulting from the lack of it.

Advancing Towards (Mental Health Care) Equality with Persuasive Technology for Mental Health

Digital discrimination is a form of discrimination whereby users are automatically treated unfairly, unethically or just differently based on their personal data by a machine learning (ML) system. Examples of digital discrimination include low-income neighbourhood’s targeted with high-interest loans or low credit scores, and women being undervalued by 21% in online marketing. Recently, different techniques and tools have been proposed to detect biases that may lead to digital discrimination. These tools often require technical expertise to be executed and for their results to be interpreted.  To allow non-technical users to benefit from ML, simpler notions and concepts to represent and reason about digital discrimination are needed. In this paper, we use norms as an abstraction to represent different situations that may lead to digital discrimination. In particular, we formalise non-discrimination norms in the context of ML systems and propose an algorithm to check whether ML systems violate these norms.

A Normative Approach to Attest Digital Discrimination

Companies have considered adoption of various high-level artificial intelligence (AI) principles for responsible AI, but there is less clarity on how to implement these principles as organizational practices. This paper reviews the principles-to-practices gap. We outline five explanations for this gap ranging from a disciplinary divide to an overabundance of tools. While some proposed approaches to responsible AI emphasize attention to a subset of ethical issues primarily in the design stage, this paper presents the measurement of real-world impacts of AI systems as a necessary shift in thinking. We argue that an impact assessment framework that is broad, operationalizable, flexible, iterative, guided, and participatory is a promising approach to close the principles-to-practices gap. To help practitioners with applying these recommendations, we review a case study of AI's use in forest ecosystem restoration, demonstrating how an impact assessment framework can translate into effective and responsible AI practices.

Principles to Practices for Responsible AI: Closing the Gap

Farmer suicide is a significant issue in several countries. This issue stems from different factors such as farmers’ inability to sell their products at the desired profit level. To help farmers get a better understanding of the future market condition, this study attempts to build a predictive model to foresee future crop price trends in various markets using a deep learning approach.

Ameliorating Farmer Suicides by Predicting Crop Price Trends using a Deep Learning Approach

"Fair inference in supervised learning is an important and active area of research, yielding a range of useful methods to assess and account for fairness criteria
when predicting ground truth targets. As shown in recent work, however, when target labels are error prone, potential prediction unfairness can arise from measurement error. In this paper, we show that, when an error-prone proxy target
is used, existing methods to assess and calibrate fairness criteria do not extend to the true target variable of interest. To remedy this problem, we suggest a framework resulting from the combination of two existing literatures: fair ML
methods, such as those found in the counterfactual fairness literature on the one hand, and, on the other, measurement models found in the statistical literature. We discuss these approaches and their connection resulting in our framework.
In a healthcare decision problem, we find that using a latent variable model to account for measurement error removes the unfairness detected previously."

Fair Inference on Error-Prone Outcomes

Information is key during a crisis such as the current COVID-19 pandemic as it greatly shapes people’s opinion, behaviour and even their psychological state. It has been acknowledged from the Secretary-General of the United Nations that the infodemic of misinformation is an important secondary crisis produced by the pandemic. Infodemics can amplify the real negative consequences of the pandemic in different dimensions: social, economic and even sanitary. For instance, infodemics can lead to hatred between population groups that fragment the society influencing its response or result in negative habits that help the pandemic propagate. On the contrary, reliable and trustful information along with messages of hope and solidarity can be used to control the pandemic, build safety nets and help promote resilience and antifragility. We propose a framework to characterize leaders in Twitter based on the analysis of the social graph derived from the activity in this social network. Centrality metrics are used to identify relevant nodes that are further characterized in terms of users’ parameters managed by Twitter. We then assess the resulting topology of clusters of leaders. Although this tool may be used for surveillance of individuals, we propose it as the basis for a constructive application to empower users with a positive influence in the collective behaviour of the network and the propagation of information.

Characterizing social leaders on Twitter during COVID-19 crisis 

"In this short article, we argue that the SDGs should figure more prominently in marking out the route to realising the potential of A/IS, while at the same time recognizing the need for a critical appraisal. We discuss how increasing awareness of an interdisciplinary research field “A/IS for development”
(A/IS4D) could contribute to achieving this, where by this term, we refer to a field that deals with the distinctive challenges posed by
A/IS technologies, particularly for more vulnerable and marginalized populations, while integrating a development studies, human-rights
centered perspective. We contend that such a perspective, and more specifically, the measuring of impact in terms of appropriate SDGs, is critical
to avoiding possible adverse effects arising from the introduction of such a disruptive technology without sufficient reflection, a real and
present danger given the current techno-optimist zeitgeist and the enormous power of the Information and Communication Technologies (ICT)
corporate sector. Unfortunately, the academic research literature of this field, like that of the more general and well-established ICT4D field, remains marginal, with contributions having little representation
in high-impact conferences and journals. This short article constitutes a modest attempt to contribute to the dissemination of this important
topic among researchers and professionals in the A/IS sector, in the way of a call for action.  "

Black-box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN

Downloads

Next from ECAI 2020

Explainable Inference in the FRANK Query Answering System

Similar lecture

Delving into the Adversarial Robustness of Federated Learning

Black-box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from ECAI 2020

Explainable Inference in the FRANK Query Answering System

Similar lecture

Delving into the Adversarial Robustness of Federated Learning

Downloads