2 papers
cs.LG2026
Reinforcing privacy reasoning in LLMs via normative simulacra from fiction
Matt Franchi, Madiha Zahrah Choksi, Harold Triedman +1
Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framewo…
cs.CY2025
Privacy of Groups in Dense Street Imagery
Matt Franchi, Hauke Sandhaus, Madiha Zahrah Choksi +3
Spatially and temporally dense street imagery (DSI) datasets have grown unbounded. In 2024, individual companies possessed around 3 trillion unique images of public streets. DSI da…