Researchers: 'Adversarial attacks' capable of producing harmful AI responses

A study by Amazon Web Services researchers has revealed critical security vulnerabilities in large language models that understand and respond to speech, which could allow them to be manipulated into generating harmful responses using sophisticated audio attacks, according to VentureBeat.

Article Link: Researchers: 'Adversarial attacks' capable of producing harmful AI responses | SC Media

1 post - 1 participant

Read full topic

adversarial adversarial attacks amazon amazon web services article attacks audio critical language language models large link producing researchers respond security services speech study understand venturebeat vulnerabilities web web services