Supervised Deanonymization of Dark Web Traffic for Cybercrime Investigation (DANON)
Type: National Project Project
Duration: from 2022 Feb 01 to 2023 Mar 31
Financed by: FCT
Prime Contractor: R - INESC-ID Lisboa (Other) - Lisboa, Portugal
In this project, we aim to develop DAnon, a software tool that allows for the deanonymization of Tor communications involved in criminal affairs on the Dark Web while preserving the privacy of its licit users. DAnon will consist of a federated network monitoring system in which multiple ISPs can cooperate cross-borders with law enforcement authorities to deanonymize Tor traffic accessing illicit Onion Services (OSes). This work will advance the state of the art on cutting-edge topics in privacy-preserving computation, machine learning, and "ethical-by-design" systems. To tackle several open challenges, we propose to investigate and combine three complementary approaches: (i) employ secure multiparty computation (MPC) protocols to enable privacy-preserving Tor OS traffic correlation, (ii) develop ML optimization techniques based on model compression and depth reduction to reduce the query latency, and (iii) incorporate quorum-based consensus between participating law enforcement agencies to reduce the chances of deanonymization abuses.
Partnerships
- FCiências.ID - Associação para a Investigação e Desenvolvimento de Ciências (Other)
- Nova.ID.FCT da Universidade Nova de Lisboa (University)
- R - INESC-ID Lisboa (Other) - Lisboa, Portugal
- R - INESC-TEC (Other)
Principal Investigators
Members
- Nuno Miguel Carvalho dos Santos (DPSS)
- Daniel Simões Lopes (AIPS)