On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction

Machine Learning as a Service (MLaaS) has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS platforms must be safeguarded against security and privacy attacks, such as model extraction (MEA) attacks. The increasing integration of explainable AI (XAI) within MLaaS has introduced an additional privacy challenge, as attackers can exploit model explanations particularly counterfactual explanations (CFs) to facilitate MEA. In this paper, we investigate the trade offs among model performance, privacy, and explainability when employing Differential Privacy (DP), a promising technique for mitigating CF facilitated MEA. We evaluate two distinct DP strategies: implemented during the classification model training and at the explainer during CF generation.

Differential Privacy for Anomaly Detection: Analyzing the Trade-off Between Privacy and Explainability

Anomaly detection (AD), also referred to as outlier detection, is a statistical process aimed at identifying observations within a dataset that significantly deviate from the expected pattern of the majority of the data. Such a process finds wide application in various fields, such as finance and healthcare. While the primary objective of AD is to yield high detection accuracy, the requirements of explainability and privacy are also paramount. The first ensures the transparency of the AD process, while the second guarantees that no sensitive information is leaked to untrusted parties. In this work, we exploit the trade-off of applying Explainable AI (XAI) through SHapley Additive exPlanations (SHAP) and differential privacy (DP). We perform AD with different models and on various datasets, and we thoroughly evaluate the cost of privacy in terms of decreased accuracy and explainability. Our results show that the enforcement of privacy through DP has a significant impact on detection accuracy and explainability, which depends on both the dataset and the considered AD model. We further show that the visual interpretation of explanations is also influenced by the choice of the AD algorithm.

How "troll" are you? Measuring and detecting troll behavior in online social networks

The detection of state-sponsored trolls acting in misinformation operations is an unsolved and critical challenge for the research community, with repercussions that go beyond the online realm. In this paper, we propose a novel approach for the detection of troll accounts, which consists of two steps. The first step aims at classifying trajectories of accounts' online activities as belonging to either a troll account or to an organic user account. In the second step, we exploit the classified trajectories to compute a metric, namely "troll score", which allows us to quantify the extent to which an account behaves like a troll. Experimental results show that our approach identifies accounts' trajectories with an AUC close to 99% and, accordingly, classify trolls and organic users with an AUC of 97%. Finally, we evaluate whether the proposed solution can be generalized to different contexts (e.g., discussions about Covid-19) and generic misbehaving users, showing promising results that will be further expanded in our future endeavors.

Combining the analytical hierarchy process and the genetic algorithm to solve the timetable problem

The main problems of school course timetabling are time, curriculum, and classrooms. In addition there are other problems that vary from one institution to another. This paper is intended to solve the problem of satisfying the teachers preferred schedule in a way that regards the importance of the teacher to the supervising institute, i.e. his score according to some criteria. Genetic algorithm (GA) has been presented as an elegant method in solving timetable problem (TTP) in order to produce solutions with no conflict. In this paper, we consider the analytic hierarchy process (AHP) to efficiently obtain a score for each teacher, and consequently produce a GA-based TTP solution that satisfies most of the teachers preferences.