JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
Maksym Andriushchenko, Patrick Chao, Francesco Croce, Edoardo Debenedetti, Edgar Dobriban, Nicolas Flammarion, Hamed Hassani, George J. Pappas, Alexander Robey, Vikash Sehwag, Florian Tramèr, Eric Wong
Topics & Concepts
Computer scienceRobustness (evolution)Artificial intelligenceBenchmark (surveying)AlgorithmData miningMachine learningLanguage modelData modelingFeature (linguistics)Authorship Attribution and ProfilingComputational and Text Analysis MethodsAdversarial Robustness in Machine Learning