A5091112545- Authorship Attribution and Profiling
- Hate Speech and Cyberbullying Detection
- Digital Media Forensic Detection
- Anomaly Detection Techniques and Applications
- Generative Adversarial Networks and Image Synthesis
- Topic Modeling
- Misinformation and Its Impacts
- Spam and Phishing Detection
- Advanced Malware Detection Techniques
- Digital and Cyber Forensics
- Cell Image Analysis Techniques
- Imbalanced Data Classification Techniques
- Natural Language Processing Techniques
- Humor Studies and Applications
- Video Surveillance and Tracking Methods
- Network Security and Intrusion Detection
- Sentiment Analysis and Opinion Mining
Centro de Tecnologia da Informação Renato Archer
2016-2023
Universidade Estadual de Campinas (UNICAMP)
2016-2023
Carnegie Mellon University
2022
The veil of anonymity provided by smartphones with pre-paid SIM cards, public Wi-Fi hotspots, and distributed networks like Tor has drastically complicated the task identifying users social media during forensic investigations. In some cases, text a single posted message will be only clue to an author's identity. How can we accurately predict who that author might when may never exceed 140 characters on service Twitter? For past 50 years, linguists, computer scientists, scholars humanities...
Learning from fully-unlabeled data is challenging in Multimedia Forensics problems, such as Person Re-Identification and Text Authorship Attribution. Recent self-supervised learning methods have shown to be effective when dealing with cases where the underlying classes significant semantic differences, intra-class distances are substantially lower than inter-class distances. However, this not case for forensic applications which similar semantics training test sets disjoint identities....
Emotions are a central driving force of activism; they motivate participation in movements and encourage sustained involvement. We use natural language processing techniques to analyze emotions expressed or solicited tweets about 2020 Black Lives Matter protests. Traditional off-the-shelf emotion analysis tools often fail generalize new datasets unable adapt how social can raise ideas perspectives short time spans. Instead, we few-shot domain adaptation approach for measuring perceived this...
The world is facing a new era in which social media communication plays fundamental role people's lives. Along with irrefutable benefits, several collateral drawbacks have risen, one being the wide spread of false information malicious intents, what now commonly called "Fake News". fight against this problem not easy, especially when taking into account nature text messages involved on platforms (a sea small and myriad users). In work, we cope challenging authorship attribution posted...
The world is facing a new era in which social media communication plays fundamental role people's lives. Along with proven benefits, several collateral drawbacks have risen, one being the widespread of false information malicious intents, oftentimes using anonymous or identities. Fighting this problem challenging, especially when considering nature text messages involved on platforms: sea small and myriad users. Attributing authorship such an ambitious endeavor; nevertheless, it way to fight...
In the last few years, social media networks have changed human life experience and behavior as it has broken down communication barriers, allowing ordinary people to actively produce multimedia content on a massive scale. On this wise, information dissemination in platforms becomes increasingly common. However, misinformation is propagated with same facility velocity real news, though can result irreversible damage an individual or society at large. Solving problem not trivial task,...
One of the major modern threats to society is propagation misinformation — fake news, science denialism, hate speech fueled by social media's widespread adoption. On leading platforms, millions automated and profiles exist only for this purpose. step mitigate problem verifying authenticity profiles, which proves be an infeasible task done manually. Recent data-driven methods accurately tackle performing automatic authorship attribution, although important aspect often overlooked: model...
RESUMO A Ciência Forense Digital surgiu da necessidade de tratar problemas forenses na era digital. Seu mais recente desafio está relacionado ao surgimento das mídias sociais, intensificado pelos avanços Inteligência Artificial. produção massiva dados nas sociais tornou a análise forense complexa, especialmente pelo aperfeiçoamento modelos computacionais capazes gerar conteúdo artificial com alto realismo. Assim, tem-se aplicação técnicas Artificial para esse imenso volume informação. Neste...
The recent computer graphics developments have upraised the quality of generated digital content, astonishing most skeptical viewer. Games and movies taken advantage this fact but, at same time, these advances brought serious negative impacts like ones yielded by fakeimages produced with malicious intents. Digital artists can compose artificial images capable deceiving great majority people, turning into a very dangerous weapon in timespan currently know as Fake News/Post-Truth" Era. In...
Social media platforms brought numerous benefits to our society, but several wrongdoings such as racism, misogyny, hate speech, anti-science statements, and large-scale misinformation came alongside. Authorship attribution is a forensics tool that can help fight against these misconducts when applied the small texts posted on platforms. In this work, we exploit recent developments in language models tackle problem of authorship messages. Training one model per suspect, devise generative...