AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Time-To-Inconsistency: A Survival Analysis of Large Language Model Robustness to Adversarial Attacks

Yubo Li, Ramayya Krishnan, Rema Padman

ICLR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language models · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Weibull AFT instead of Cox Baselinetime-to-inconsistency model · MT-Consistency testIBS: 0.344 -> 0.180Improved
use Weibull AFT instead of Cox Baselinetime-to-inconsistency model · MT-Consistency testC-index: 0.861 -> 0.874Improved
add model-drift interaction terms to Weibull AFT (ablation)Weibull AFT · MT-Consistency testIBS: 0.180 -> 0.175Improved
add model-drift interaction terms to Weibull AFT (ablation)Weibull AFT · MT-Consistency testC-index: 0.874 -> 0.869Hurt
add model-drift interaction terms to Cox (ablation)Cox Baseline · MT-Consistency testC-index: 0.861 -> 0.868Improved
add model-drift interaction terms to Cox (ablation)Cox Baseline · MT-Consistency testIBS: 0.344 -> 0.343No clear effect
use log-logistic instead of Weibull AFT family (ablation)AFT · MT-Consistency testIBS: 0.180 -> 0.187Hurt
use Weibull AFT instead of Random Survival Forestsurvival model · MT-Consistency testC-index: 0.845 -> 0.874Improved
use Weibull AFT instead of Random Survival Forestsurvival model · MT-Consistency testIBS: 0.190 -> 0.180Improved
use AFT instead of Cox for late-round calibrationtime-to-inconsistency model · MT-Consistency test round 8Brier score: 0.446 -> 0.027Improved
use AFT-based monitor instead of drift-threshold baselinerisk monitor · failing conversations% alerted: 62% -> 76%Improved
use AFT-based monitor instead of drift-threshold baselinerisk monitor · censored conversations% alerted: 32% -> 19%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy