Work

Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis

Year: 2026

Type: conference-paper

Abstract: This paper discusses adversarial jailbreak attacks on large language models, including references to harmful content categories.This material is presented solely for the purpose of scientific research and does not reflect the views of the authors.

Source: Workshop on Trustworthy NLP (TrustNLP)

DOI: 10.18653/v1/2026.trustnlp-main.5

Author: Zvi Topol

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166856412

FWCI:

Cites:

Cited by:

Related to: 10