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, the quality of the images from the human perception point of view is maintained. Several experiments with different sequences of filters are run and show that the Attack Success Rate is very high, above 90% for every test.
Determining the appropriate binary correlation indexes is a central issue for neighbourhood-based Link Prediction techniques. In those approaches correlation-based similarity measures, evaluated on the neighbourhood of a given pair of nodes in a training network, are used to assess the likelihood of those nodes developing new links in the future. It has been observed that, although some similarity measures generally perform better than others, no single binary correlation is optimal for all domains. In this work we introduce a technique which evolves a population of correlation indexes, using a Differential Evolution (DE) algorithm, in order to determine the binary correlation index having the best prediction performance with respect to specific network domains. DE evolves the parameters of meta-indexes, structures which describe and extend classes of known binary similarity indexes. Preliminary experiments show that the proposed correlation indexes evolution method has performances equivalent and in some cases improving the best correlation indexes known for each tested domain, while it provides the remarkable advantage of domain self-adaptability.
Implicit hate speech (IHS) is indirect language that conveys prejudice or hatred through subtle cues, sarcasm or coded terminology. IHS is challenging to detect as it does not include explicit derogatory or inflammatory words. To address this challenge, task-specific pipelines can be complemented with external knowledge or additional information such as context, emotions and sentiment data. In this paper, we show that, by solely fine-tuning recent general-purpose embedding models based on large language models (LLMs), such as Stella, Jasper, NV-Embed and E5, we achieve state-of-the-art performance. Experiments on multiple IHS datasets show up to 1.10 percentage points improvements for in-dataset, and up to 20.35 percentage points improvements in cross-dataset evaluation, in terms of F1-macro score.