Abstract
As blockchains go beyond cryptocurrencies into applications in multiple industries such as Insurance, Healthcare and Banking, handling personal or sensitive data, data access control becomes increasingly relevant. Access control mechanisms proposed so far are mostly based on requester identity, particularly for permissioned blockchain platforms, and are limited to binary, all-or-nothing access decisions. This is the case with Hyperledger Fabric's native access control mechanisms and, as permission updates require consensus, these fall short regarding the flexibility required to address GDPR-derived policies and client consent management. We propose SDAM, a novel access control mechanism for Fabric that enables fine-grained and dynamic control policies, using both contextual and resource attributes for decisions. Instead of binary results, decisions may also include mandatory data transformations as to conform with the expressed policy, all without modifications to Fabric. Results show that SDAM's overhead w.r.t baseline Fabric is acceptable. The scalability of the approach w.r.t to the number of concurrent clients is also evaluated and found to follow Fabric's.

Abstract
Tor is the most popular anonymity network in the world. It relies on advanced security and obfuscation techniques to ensure the privacy of its users and free access to the Internet. However, the investigation of traffic correlation attacks against Tor Onion Services (OSes) has been relatively overlooked in the literature. In particular, determining whether it is possible to emulate a global passive adversary capable of deanonymizing the IP addresses of both the Tor OSes and of the clients accessing them has remained, so far, an open question. In this paper, we present ongoing work toward addressing this question and reveal some preliminary results on a scalable traffic correlation attack that can potentially be used to deanonymize Tor OS sessions. Our attack is based on a distributed architecture involving a group of colluding ISPs from across the world. After collecting Tor traffic samples at multiple vantage points, ISPs can run them through a pipeline where several stages of traffic classifiers employ complementary techniques that result in the deanonymization of OS sessions with high confidence (i.e., low false positives). We have responsibly disclosed our early results with the Tor Project team and are currently working not only on improving the effectiveness of our attack but also on developing countermeasures to preserve Tor users' privacy.

Abstract
The application of machine learning to insurance risk prediction requires learning from sensitive data. This raises multiple ethical and legal issues. One of the most relevant ones is privacy. However, privacy-preserving methods can potentially hinder the predictive potential of machine learning models. In this paper, we present preliminary experiments with life insurance data using two privacy-preserving techniques: discretization and encryption. Our objective with this work is to assess the impact of such privacy preservation techniques in the accuracy of ML models. We instantiate the problem in three general, but plausible Use Cases involving the prediction of insurance claims within a 1-year horizon. Our preliminary experiments suggest that discretization and encryption have negligible impact in the accuracy of ML models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Angola is characterized by many different languages and social, cultural and political realities, which had a marked effect on Angolan Portuguese (AP). Consequently, AP is characterized by diatopic variation. One of the marked effects is the loanwords imported from other Angolan languages. Our objective is to analyze different Angolan texts, analyze the lexical forms used and conduct a comparative study with European Portuguese, aiming at identifying the possible loanwords in Angolan Portuguese. This process was automated, as well as the identification of all loanwords' cotexts. In addition, we determine the lexical class of each loanword and the Angolan language of its origin. Most lexical loanwords come from the Kimbundu, although AP includes loanwords from some other Angolan languages too. Our study serves as a basis for preparing an Angolan regionalism dictionary. We noticed that more than 700 identified loanwords do not figure in the existing dictionaries.

Abstract
This paper describes two different approaches to sentiment analysis. The first is a form of symbolic approach that exploits a sentiment lexicon together with a set of shifter patterns and rules. The sentiment lexicon includes single words (unigrams) and is developed automatically by exploiting labeled examples. The shifter patterns include intensification, attenuation/downtoning and inversion/reversal and are developed manually. The second approach exploits a deep neural network, which uses a pre-trained language model. Both approaches were applied to texts on economics and finance domains from newspapers in European Portuguese. We show that the symbolic approach achieves virtually the same performance as the deep neural network. In addition, the symbolic approach provides understandable explanations, and the acquired knowledge can be communicated to others. We release the shifter patterns to motivate future research in this direction.

Abstract