DeepLocker: How AI [anda facial recognition] Can Power a Stealthy New Breed of Malware
Appoggiandosi a un tool open source di reidintificazione su SN (Social Mapper <https://github.com/SpiderLabs/social_mapper>) IBM research dimostra la "fattibilità" di un cryptolocker (o cyberweapon generica) mirato sulla singola persona. In effetti ne sentivamo la mancanza... <https://securityintelligence.com/deeplocker-how-ai-can-power-a-stealthy-new-...> [] IBM Research developed DeepLocker to better understand how several existing AI models can be combined with current malware techniques to create a particularly challenging new breed of malware. This class of AI-powered evasive malware conceals its intent until it reaches a specific victim. It unleashes its malicious action as soon as the AI model identifies the target through indicators like facial recognition, geolocation and voice recognition. You can think of this capability as similar to a sniper attack, in contrast to the “spray and pray” approach of traditional malware. DeepLocker is designed to be stealthy. It flies under the radar, avoiding detection until the precise moment it recognizes a specific target. This AI-powered malware is particularly dangerous because, like nation-state malware, it could infect millions of systems without being detected. But, unlike nation-state malware, it is feasible in the civilian and commercial realms. [] Penso che la cosa veramente nuova sia il tool di reidentificazione aperto (con licenza GPL). Se uno strumento di questo tipo sia o no una buona cosa per la privacy è una domanda che mi sono posto nel 2012 in questo paper <http://sedici.unlp.edu.ar/bitstream/handle/10915/23870/Documento_completo.pd...> Comunque un ulteriore buon motivo per mascherare l'obiettivo della webcam.
participants (1)
-
Alberto Cammozzo