UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
Isolation forest
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
KRONE derives semantic execution hierarchies from flat logs to enable modular multi-level anomaly detection with hybrid local and nested-aware detectors plus limited LLM use, delivering 10% F1 gains and over 100x data efficiency on benchmarks and industrial data.
RTTAD improves unsupervised tabular anomaly detection by combining collaborative dual-task learning during training with selective, risk-aware test-time contrastive learning that avoids anomaly contamination.
GiB uses self-supervised latent features and Mahalanobis distance to filter erroneous subtasks from mixed-quality human demonstrations, improving robot policy learning in simulation and real-world tasks.
PLAG boosts tabular anomaly detection by using pseudo-label-guided synthetic anomaly generation with a two-stage filter, achieving SOTA results and lifting F1 scores by 0.08-0.21 when added to existing detectors.
FABLE applies 3D discrete wavelet decomposition to generate localized adversarial perturbations that steer deep learning weather forecasting models toward chosen forecast outcomes while keeping inputs close to the originals.
DyMETER unifies hypernetwork-driven parameter adaptation and dynamic thresholding for online anomaly detection under concept drift.
T-BiGAN integrates window-attention Transformers in a BiGAN to achieve ROC-AUC 0.95 and average precision 0.996 for unsupervised spatiotemporal anomaly detection in PMU data.
citing papers explorer
-
Membership Inference for Contrastive Pre-training Models with Text-only PII Queries
UMID infers membership in contrastive pre-training data using only text queries by performing latent inversion and comparing similarity and variability signals to synthetic gibberish references via unsupervised anomaly detection.
-
KRONE: Scalable LLM-Augmented Log Anomaly Detection via Hierarchical Abstraction
KRONE derives semantic execution hierarchies from flat logs to enable modular multi-level anomaly detection with hybrid local and nested-aware detectors plus limited LLM use, delivering 10% F1 gains and over 100x data efficiency on benchmarks and industrial data.
-
When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection
RTTAD improves unsupervised tabular anomaly detection by combining collaborative dual-task learning during training with selective, risk-aware test-time contrastive learning that avoids anomaly contamination.
-
Good in Bad (GiB): Sifting Through End-user Demonstrations for Learning a Better Policy
GiB uses self-supervised latent features and Mahalanobis distance to filter erroneous subtasks from mixed-quality human demonstrations, improving robot policy learning in simulation and real-world tasks.
-
Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation
PLAG boosts tabular anomaly detection by using pseudo-label-guided synthetic anomaly generation with a two-stage filter, achieving SOTA results and lifting F1 scores by 0.08-0.21 when added to existing detectors.
-
FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models
FABLE applies 3D discrete wavelet decomposition to generate localized adversarial perturbations that steer deep learning weather forecasting models toward chosen forecast outcomes while keeping inputs close to the originals.
-
Catching Every Ripple: Enhanced Anomaly Awareness via Dynamic Concept Adaptation
DyMETER unifies hypernetwork-driven parameter adaptation and dynamic thresholding for online anomaly detection under concept drift.
-
Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN
T-BiGAN integrates window-attention Transformers in a BiGAN to achieve ROC-AUC 0.95 and average precision 0.996 for unsupervised spatiotemporal anomaly detection in PMU data.