4 citations · 7 across the 5 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CR2023★ 2 cited
Maatphor: Automated Variant Analysis for Prompt Injection Attacks
Ahmed Salem, Andrew Paverd, Boris Köpf
Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injec…
cs.LG2023★ 1 cited
Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective
Lukas Wutschitz, Boris Köpf, Andrew Paverd +6
Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during traini…