Gandalf the Red: Adaptive Security for LLMs

no code implementations • 14 Jan 2025 • Niklas Pfister, Václav Volhejn, Manuel Knott, Santiago Arias, Julia Bazińska, Mykhailo Bichurin, Alan Commike, Janet Darling, Peter Dienes, Matthew Fiedler, David Haber, Matthias Kraft, Marco Lancini, Max Mathys, Damián Pascual-Ortiz, Jakub Podolak, Adrià Romero-López, Kyriacos Shiarlis, Andreas Signer, Zsolt Terek, Athanasios Theocharis, Daniel Timbrell, Samuel Trautwein, Samuel Watts, Natalie Wu, Mateo Rojas-Carulla

Current evaluations of defenses against prompt attacks in large language model (LLM) applications often overlook two critical factors: the dynamic nature of adversarial behavior and the usability penalties imposed on legitimate users by restrictive defenses.

Blocking Language Modeling +3

Recommendations on test datasets for evaluating AI solutions in pathology

no code implementations • 21 Apr 2022 • André Homeyer, Christian Geißler, Lars Ole Schwen, Falk Zakrzewski, Theodore Evans, Klaus Strohmenger, Max Westphal, Roman David Bülow, Michaela Kargl, Aray Karjauv, Isidre Munné-Bertran, Carl Orge Retzlaff, Adrià Romero-López, Tomasz Sołtysiński, Markus Plass, Rita Carvalho, Peter Steinbach, Yu-Chia Lan, Nassim Bouteldja, David Haber, Mateo Rojas-Carulla, Alireza Vafaei Sadr, Matthias Kraft, Daniel Krüger, Rutger Fick, Tobias Lang, Peter Boor, Heimo Müller, Peter Hufnagl, Norman Zerbe

The recommendations are intended to help AI developers demonstrate the utility of their products and to help regulatory agencies and end users verify reported performance measures.