LidaSafety/fragbench download history
LidaSafety/fragbench is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 3,366 times (277 in the last 7 days), and 14,699 times in total. It ranks #7,646 among datasets by monthly downloads.
FragBench (Public Tier) Anonymous submission to ICLR 2027. Author identity will be revealed at camera-ready. Dataset Summary FragBench is a benchmark for evaluating cross-session, fragmented attacks on LLM agents that use tools via the Model Context Protocol (MCP). Each