Synthetic network generators preserve cross-flow correlations enabling source-level membership inference, shown via the TraceBleed attack across five datasets and six generators.
arXiv preprint arXiv:1907.00503 (2019)
9 Pith papers cite this work, alongside 94 external citations. Polarity classification is still indexing.
9
Pith papers citing it
94
external citations · external index
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
ICL in LLMs shows a sharp ceiling on categorical distributions for high-cardinality tabular data, failing to reproduce rare classes despite examples, while numerical fidelity improves.
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.
Adversaries can degrade synthetic data quality via small manipulations such as label flipping or feature-importance interventions, substantially harming downstream model performance and increasing statistical divergence from real data.
Seq. RC-TGAN adds a spectral envelope loss to RC-TGAN and uses VGM discretization plus simulated benchmarks with known envelopes to generate relational time series that better match frequency-domain features.
After correcting prior flaws, a class-dependent hybrid augmentation strategy plus clinical subtype aggregation raises average macro-F1 robustness across eight classifiers on a 400-patient seven-subtype migraine dataset, with peak 0.914 under proportional growth.
DECAF synthetic data generator best balances privacy and fairness while fairness pre-processing improves outcomes more on synthetic data than real data, though at some cost to predictive accuracy.
Context-conditioned normalizing flows refine subnational survey distributions under severe data scarcity when conditioning covariates capture local heterogeneity.
citing papers explorer
-
Cross-Flow Correlations Survive Synthesis: Measuring Source-Level Privacy Leakage in Synthetic Network Traces
Synthetic network generators preserve cross-flow correlations enabling source-level membership inference, shown via the TraceBleed attack across five datasets and six generators.
-
Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
ICL in LLMs shows a sharp ceiling on categorical distributions for high-cardinality tabular data, failing to reproduce rare classes despite examples, while numerical fidelity improves.
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
COMPASS: A Unified Decision-Intelligence System for Navigating Performance Trade-off in HPC
COMPASS formalizes HPC configuration questions as ML tasks on traces, quantifies recommendation trustworthiness, and delivers 65.93% lower average job turnaround time plus 80.93% lower node usage versus prior methods in simulator tests.
-
Quality Degradation Attack in Synthetic Data
Adversaries can degrade synthetic data quality via small manipulations such as label flipping or feature-importance interventions, substantially harming downstream model performance and increasing statistical divergence from real data.
-
Sequential RC-TGAN: Generating Relational Time Series with Spectral Envelope Loss
Seq. RC-TGAN adds a spectral envelope loss to RC-TGAN and uses VGM discretization plus simulated benchmarks with known envelopes to generate relational time series that better match frequency-domain features.
-
Class-Dependent Hybrid Data Augmentation for Multiclass Migraine Classification under Severe Class Imbalance
After correcting prior flaws, a class-dependent hybrid augmentation strategy plus clinical subtype aggregation raises average macro-F1 robustness across eight classifiers on a 400-patient seven-subtype migraine dataset, with peak 0.914 under proportional growth.
-
Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms
DECAF synthetic data generator best balances privacy and fairness while fairness pre-processing improves outcomes more on synthetic data than real data, though at some cost to predictive accuracy.
-
Context-Conditioned Generative Models Enable Subnational Refinement of Sparse Humanitarian Surveys
Context-conditioned normalizing flows refine subnational survey distributions under severe data scarcity when conditioning covariates capture local heterogeneity.