idSCD: Identifying Training Datasets through Semantic Correlation Descriptors
cs.LG, cs.AI
Submitted: 2026-05-28
Updated: 2026-10-12
Terminology
Sources
- Invariant Risk Minimization
- Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
- Label-Only Membership Inference Attacks
- Membership Inference Attack Using Self Influence Functions
- PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts
- Shortcut Learning of Large Language Models in Natural Language Understanding
- Shortcut Learning in Deep Neural Networks
- Annotation Artifacts in Natural Language Inference Data
- On Feature Learning in the Presence of Spurious Correlations
- Understanding Black-box Predictions via Influence Functions
- Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
- Membership Leakage in Label-Only Exposures
- Membership Inference Attacks by Exploiting Loss Trajectory
- LLM Dataset Inference: Did you train on my dataset?
- Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference
- Machine Learning with Membership Privacy using Adversarial Regularization
- Probing Neural Network Comprehension of Natural Language Arguments
- TRAK: Attributing Model Behavior at Scale
- OSLO: One-Shot Label-Only Membership Inference Attacks
- White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks