Privacy

FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning ICCV 2025 Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs Without Real Data Replay AAAI 2025 Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning ICCV 2025 Fine-Grained and Efficient Self-Unlearning with Layered Iteration IJCAI 2025 Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models CVPR 2025 Fine-grained Prompt Screening: Defending Against Backdoor Attack on Text-to-Image Diffusion Models IJCAI 2025 Fine-tuning can Help Detect Pretraining Data from Large Language Models ICLR 2025 Fingerprinting Denoising Diffusion Probabilistic Models CVPR 2025 FLSeg: Enhancing Privacy and Robustness in Federated Learning under Heterogeneous Data via Model Segmentation ICCV 2025 FMD: Comprehensive Data Compression in Medical Domain via Fused Matching Distillation WACV 2025 Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems ICLR 2025 Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning EMNLP 2025 Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage AAAI 2025 Fortifying Federated Learning Towards Trustworthiness via Auditable Data Valuation and Verifiable Client Contribution CVPR 2025 From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs ACL 2025 From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning CVPR 2025 From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification CVPR 2025 Fully Test-Time Adaptation for Feature Decrement in Tabular Data IJCAI 2025 Fundamental Limits of Membership Inference Attacks on Machine Learning Models JMLR 2025 Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation AAAI 2025 Generating Synthetic Free-text Medical Records with Low Re-identification Risk using Masked Language Modeling NAACL 2025 GeoSAFE - A Novel Geospatial Artificial Intelligence Safety Assurance Framework and Evaluation for LLM Moderation IJCNLP 2025 Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization COLING 2025 GIL-IIMAS UNAM at SemEval-2025 Task 4: LA-Min(E): LLM Unlearning Approaches Under Function Minimizing Evaluation Constraints SemEval 2025 Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining COLING 2025