conftrace_

membership inference attack

93 papers

Explore in graph

Also known as

MIA

Co-occurring keywords

membership inference (114) privacy attack (119) large language model (13587) differential privacy (1016) privacy risk (42) privacy leakage (105) privacy preservation (380) language model (4599) adversarial attack (1621) federated learning (1333)

Papers

TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025
Federated Graph Condensation with Information Bottleneck Principles AAAI 2025
Membership Inference Attacks with False Discovery Rate Control ICCV 2025
FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning CVPR 2025
EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint EMNLP 2025
Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? AAAI 2025
MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector AAAI 2025
Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning ICCV 2025
Multi-modal Identity Extraction ICCV 2025
Public Data Assisted Differentially Private In-Context Learning EMNLP 2025
Tracing Training Footprints: A Calibration Approach for Membership Inference Attacks Against Multimodal Large Language Models EMNLP 2025
Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models CVPR 2025
OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models IJCAI 2025
Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models AAAI 2025
Sampling-based Pseudo-Likelihood for Membership Inference Attacks ACL 2025
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training ACL 2025
Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home? EMNLP 2025
Personalized Language Models via Privacy-Preserving Evolutionary Model Merging EMNLP 2025
Towards More Realistic Membership Inference Attacks on Large Diffusion Models WACV 2024
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions NIPS 2024
ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods EMNLP 2024
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models NIPS 2024
Locally Differentially Private In-Context Learning COLING 2024
OSLO: One-Shot Label-Only Membership Inference Attacks NIPS 2024