4 papers
FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing
Yuhan Ma, Yong Li, Stefan Schmid
Two-server secure inference allows a client to query a hosted large language model (LLM) without revealing prompts or embeddings. Recent GPU systems based on function secret sharin…
SecureClaw: Clawing Back Control of LLM Agents
Yuhan Ma, Stefan Schmid
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any fi…
Friend or Foe? Identifying Anomalous Peers in Moneros P2P Network
Yannik Kopyciok, Stefan Schmid, Friedhelm Victor
Monero, the leading privacy-focused cryptocurrency, relies on a peer-to-peer (P2P) network to propagate transactions and blocks. Growing evidence suggests that non-standard nodes e…
Moneros Decentralized P2P Exchanges: Functionality, Adoption, and Privacy Risks
Yannik Kopyciok, Friedhelm Victor, Stefan Schmid
Privacy-focused cryptocurrencies like Monero remain popular, despite increasing regulatory scrutiny that has led to their delisting from major centralized exchanges. The latter als…