← Search

Katerina Sotiraki

1 accepted papers

2024

Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models

NeurIPS 2024poster

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors, as defined in Goldwasser et al. [2022], in models developed…

Cited by 1SourcePDFScholar