Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility - 惯性聚合

推荐订阅源

博客园 - Franky

Proofpoint News Feed

Palo Alto Networks Blog

Hackread – Cybersecurity News, Data Breaches, AI and More

The Register - Security

Security @ Cisco Blogs

Simon Willison's Weblog

Recorded Future

大猫的无限游戏

Microsoft Research Blog - Microsoft Research

Tailwind CSS Blog

cs.CV updates on arXiv.org

Cyber Security Advisories - MS-ISAC

Application and Cybersecurity Blog

True Tiger Recordings

有赞技术团队

Cisco Talos Blog

Hacker News - Newest: "LLM"

The GitHub Blog

cs.AI updates on arXiv.org

博客园 - 叶小钗

Hugging Face - Blog

Hacker News: Ask HN

Security Archives - TechRepublic

Future of Privacy Forum

PCI Perspectives

Help Net Security

让小产品的独立变现更简单 - ezindie.com

The Blog of Author Tim Ferriss

Netflix TechBlog - Medium

罗磊的独立博客

Apple Machine Learning Research

Security Latest

美团技术团队

博客园 - 三生石上(FineUI控件)

Schneier on Security

CERT Recently Published Vulnerability Notes

cs.LG updates on arXiv.org

Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics Support-aware offline policy selection for advertising marketplaces DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift Richer Bayesian Last Layers with Subsampled NTK Features Aerodynamic force reconstruction using physics-informed Gaussian processes Evaluation of Pipelines for Data Integration into Knowledge Graphs Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning Symbolic Density Estimation for Discrete Distributions The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity Manifold-Guided Attention Steering PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs Thermodynamic Irreversibility of Training Algorithms AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review IKNO: Infinite-order Kernel Neural Operators AgForce Enables Antigen-conditioned Generative Antibody Design Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring $\textit{BlockFormer}$ : Transformer-based inference from interaction maps Predicting Performance of Symbolic and Prompt Programs with Examples Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs Harnesses for Inference-Time Alignment over Execution Trajectories ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study CausalGuard: Conformal Inference under Graph Uncertainty Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition Bandit Convex Optimization with Gradient Prediction Adaptivity When to Switch, Not Just What: Transition Quality Prediction in Clash Royale Toward Understanding Adversarial Distillation: Why Robust Teachers Fail Provable Joint Decontamination for Benchmarking Multiple Large Language Models PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift Three Costs of Amortizing Gaussian Process Inference with Neural Processes Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines How Many Different Outputs Can a Transformer Generate? Skill Weaving: Efficient LLM Improvement via Modular Skillpacks Double descent for least-squares interpolation on contaminated data: A simulation study MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation Tabular foundation models for robust calibration of near-infrared chemical sensing data Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning Dynamic Mixture of Latent Memories for Self-Evolving Agents One-Way Policy Optimization for Self-Evolving LLMs Noise Schedule Design for Diffusion Models: An Optimal Control Perspective What are the Right Symmetries for Formal Theorem Proving? Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling Can Transformers Learn to Verify During Backtracking Search? SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization

Provably Protecting Fine-Tuned LLMs from Training Data Extraction while Preserving Utility

Tom Segal, A · 2026-05-23 · via cs.LG updates on arXiv.org

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。