Paper to Read (Agent Safety Benchmark) - a naufalso Collection

naufalso 's Collections

Paper to Read (Agent Safety Benchmark)

Paper to Read (LLM Training and Function Calling)

LLM in Cybersecurity

State-of-the-art Open-Source LLM (General)

Paper to Read (Agent Safety Benchmark)

updated 22 days ago

List of Paper for AI Agent Safety Benchmark

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Paper • 2410.09024 • Published Oct 11, 2024 • 1
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Paper • 2410.02644 • Published Oct 3, 2024
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Paper • 2402.04249 • Published Feb 6, 2024 • 6