LLM Security(@llm_sec):InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models (-- look at that perf/latency pareto frontier. game on!) "State-of-the-art models suffer from over-defense issues, with accuracy dropping close to random guessing levels (60%). We propose InjecGuard, a novel prompt guard model that incorporates a new training strategy, Mitigating Over-defense for Free (MOF). InjecGuard demonstrates state-of-the-art performance on diverse benchmarks, surpassing the existing best model by 30.8%" code: https://t.co/XbR6FF2tPc paper: https://t.co/WWXAWCEjwL (not peer reviewed)

LLM Security

@llm_sec

Research, papers, jobs, and news on large language model security. Got something relevant? DM / tag @llm_sec

参加 April 2023

292 フォロー中 9.8K ファン

LLM Security@llm_sec

2024.11.05 16:59

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models (-- look at that perf/latency pareto frontier. game on!) "State-of-the-art models suffer from over-defense issues, with accuracy dropping close to random guessing levels (60%). We propose InjecGuard, a novel prompt guard model that incorporates a new training strategy, Mitigating Over-defense for Free (MOF). InjecGuard demonstrates state-of-the-art performance on diverse benchmarks, surpassing the existing best model by 30.8%" code: paper: (not peer reviewed)