Social Media as a Catalyst for Inclusion and Solidarity: Challenges and Opportunities

Abstract

In today's digital revolution, social media platforms have extended their initial purposes and emerged as potential tool for promoting inclusion, solidarity, and positive change. The talk will present a comprehensive exploration of the crucial role of social media in our society. It will outline how these platforms can serve as a potential tool for learning, skill development, and human empowerment while remaining cost-effective. It will also present the advantages presented by Social Media platforms by focusing on their influence on individuals and communities.

On the other hand, the talk will address the negative aspects of social media by overviewing the big issues of online harassment, in particular its impact on women and children. The importance of regulations and safeguards to protect vulnerable users in the digital era.

GAN fingerprint for active detection/attribution of fake media

Abstract

The continuous progress of generative models is fostering impressive advances in a variety of applications ranging from videoconferencing through virtual reality, passing from fast and seamingless creation of personalized media. At the same time, the availability of increasingly powerful tools for the generation of synthetic contents raises concerns about the possibility of distinguishing synthetic and genuine contents. Possible misuses of generative models, in fact, include the creation of fake media to support misinformation campaigns, defamation, polarization of public opinion and so on. For this reason, several multimedia forensic techniques have been developed to distinguish fake and real contents and trace back the manipulation history of any piece of media. However, such techniques fall short of keeping the pace of technological advancements, in addition they are not suitable to be applied in the wild even because they rely on subtle traces that are usually washed away by common processing tools (e.g. lossy compression). In this talk, I will advocate the use of active forensics techniques relying on the introduction within the to-be-authenticated content of a unique fingerprint (a.k.a. watermark). The fingerprint should be introduced within the media at creation time and should not be possible to remove it without degrading the hosting content in a significant way. In contrast to classical watermarking, here the fingerprint is embedded within the generative model, rather than directly in the generated content. In fact, to retain its effectiveness the generative models should still introduce a detectable fingerprint also in the presence of model finetuning, pruning and compression. In this talk, I will outline the main challenges and opportunities associated to generative model fingerprinting and briefly review the state of the art of this rapidly evolving area.

Optimal Deep Graph Learning: Towards a New Frontier

Abstract

The emergence of deep learning models designed for graph and network data, often under an umbrella term named graph neural networks (GNNs for short), has largely streamlined many graph learning problems. In the vast majority of the existing works, they aim to answer the following question, that is, given a graph, what is the best GNNs model to learn from it? In this talk, we introduce the graph sanitation problem, to answer an orthogonal question. That is, given a mining task and an initial graph, what is the best way to improve the initially provided graph? We formulate the graph sanitation problem as a bilevel optimization problem, and further instantiate it by semi-supervised node classification, together with an effective solver named Gasoline. I will also introduce other works we recently did centered around learning optimal graphs, and share my vision for the future directions.