Forensic Event Analysis: From Seemingly Unrelated Data to Understanding

Rodrigues, Caroline Mazini; Andaló, Fernanda A.; Bertocco, Gabriel; Dias, Zanoni; Rocha, Anderson

doi:10.1109/msec.2020.3000446

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…I n the November/December 2020 issue of IEEE Security & Privacy, there was an error in a biography in Padilha et al 1 The bio of Gabriel Bertocco should read as follows:…”

Section: Erratamentioning

confidence: 99%

Attacks on Artificial Intelligence [Last Word]

Bertino

2021

IEEE Secur. Privacy

View full text Add to dashboard Cite

“…I n the November/December 2020 issue of IEEE Security & Privacy, there was an error in a biography in Padilha et al 1 The bio of Gabriel Bertocco should read as follows:…”

Section: Erratamentioning

confidence: 99%

Attacks on Artificial Intelligence [Last Word]

Bertino

2021

IEEE Secur. Privacy

View full text Add to dashboard Cite

“…One of the main goals when dealing with forensic problems is to answer "who took part in an event?". Person ReID comprises the primary techniques to find possible people, or groups of people, involved in an event and to, ultimately, propose candidate suspects for further investigation [1].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised and self-adaptative techniques for cross-domain person re-identification

Bertocco¹,

Andaló²,

Rocha³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Person Re-Identification (ReID) across nonoverlapping cameras is a challenging task and most works in the prior art rely on supervised feature learning from a labeled dataset to match the same person in different views. However, it demands the time-consuming task of labeling the acquired data, prohibiting its fast deployment in forensic scenarios. Unsupervised Domain Adaptation (UDA) emerges as a promising alternative, as it performs feature adaptation from a model trained on a source to a target domain without identitylabel annotation. However, most UDA-based methods rely upon a complex loss function with several hyper-parameters, which hinders the generalization to different scenarios. Moreover, as UDA depends on the translation between domains, it is important to select the most reliable data from the unseen domain, avoiding error propagation caused by noisy examples on the target data -an often overlooked problem. In this sense, we propose a novel UDA-based ReID method that optimizes a simple loss function with only one hyper-parameter and takes advantage of triplets of samples created by a new offline strategy based on the diversity of cameras within a cluster. This new strategy adapts and regularizes the model, avoiding overfitting on the target domain. We also introduce a new self-ensembling strategy, in which weights from different iterations are aggregated to create a final model combining knowledge from distinct moments of the adaptation. For evaluation, we consider three well-known deep learning architectures and combine them for final decision-making. The proposed method does not use person re-ranking nor any label on the target domain, and outperforms the state of the art, with a much simpler setup, on the Market to Duke, the challenging Market1501 to MSMT17, and Duke to MSMT17 adaptation scenarios.

show abstract

“…Tal volume de dados gera inúmeros desafios nas etapas do processo forense (Padilha et al, 2020). Uma vez que os dados referentes a um evento -como imagens, vídeos e texto -tenham sido coletados, a primeira etapa consiste em filtrar as informações relevantes.…”

unclassified

A Inteligência Artificial e os desafios da Ciência Forense Digital no século XXI

et al. 2021

Self Cite

View full text Add to dashboard Cite

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 da Inteligência Artificial. A produção massiva de dados nas mídias sociais tornou a análise forense mais complexa, especialmente pelo aperfeiçoamento de modelos computacionais capazes de gerar conteúdo artificial com alto realismo. Assim, tem-se a necessidade da aplicação de técnicas de Inteligência Artificial para tratar esse imenso volume de informação. Neste artigo, apresentamos desafios e oportunidades associados à aplicação dessas técnicas, além de fornecer exemplos de seu uso em situações reais. Discutimos os problemas que surgem em contextos sensíveis e como a comunidade científica tem abordado esses tópicos. Por fim, delineamos futuros caminhos de pesquisa a serem explorados.

show abstract

Forensic Event Analysis: From Seemingly Unrelated Data to Understanding

Cited by 4 publications

References 16 publications

Attacks on Artificial Intelligence [Last Word]

Attacks on Artificial Intelligence [Last Word]

Unsupervised and self-adaptative techniques for cross-domain person re-identification

A Inteligência Artificial e os desafios da Ciência Forense Digital no século XXI

Contact Info

Product

Resources

About