Publications (7)
Machine Learning (In) Security: A Stream of Problems
FabrÃcio Ceschin, Marcus Botacin, Albert Bifet +4
Machine Learning (ML) has been widely applied to cybersecurity and is considered state-of-the-art for solving many of the open issues in that field. However, it is very difficult t…
ML-Based Behavioral Malware Detection Is Far From a Solved Problem
Yigitcan Kaya, Yizheng Chen, Marcus Botacin +5
Malware detection is a ubiquitous application of Machine Learning (ML) in security. In behavioral malware analysis, the detector relies on features extracted from program execution…
A Praise for Defensive Programming: Leveraging Uncertainty for Effective Malware Mitigation
Ruimin Sun, Marcus Botacin, Nikolaos Sapountzis +6
A promising avenue for improving the effectiveness of behavioral-based malware detectors would be to combine fast traditional machine learning detectors with high-accuracy, but tim…
A [in]Segurança dos Sistemas Governamentais Brasileiros: Um Estudo de Caso em Sistemas Web e Redes Abertas
Marcus Botacin, André Grégio
Whereas the world relies on computer systems for providing public services, there is a lack of academic work that systematically assess the security of government systems. To parti…
Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction
Seyyed Ali Ayati, Jin Hyun Park, Yichen Cai +1
The large integration of microphones into devices increases the opportunities for Acoustic Side-Channel Attacks (ASCAs), as these can be used to capture keystrokes' audio signals t…
Fast & Furious: Modelling Malware Detection as Evolving Data Streams
FabrÃcio Ceschin, Marcus Botacin, Heitor Murilo Gomes +3
Malware is a major threat to computer systems and imposes many challenges to cyber security. Targeted threats, such as ransomware, cause millions of dollars in losses every year. T…
Malware MultiVerse: From Automatic Logic Bomb Identification to Automatic Patching and Tracing
Marcus Botacin, André Grégio
Malware and other suspicious software often hide behaviors and components behind logic bombs and context-sensitive execution paths. Uncovering these is essential to react against m…