Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis

Abstract

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary success/failure metrics, failing to capture the temporal dynamics of how attacks succeed under persistent adversarial pressure. This preliminary work proposes a novel evaluation framework that applies survival analysis techniques to characterize LLM jailbreak v

Categories

Framework mappings

Suggested from the entry's categories.

@misc{topol2026quantifying,
  title = {{Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis}},
  author = {Zvi Topol},
  year = {2026},
  month = may,
  eprint = {2605.12869},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.12869}
}