70 lines (70 loc) · 13.6 KB

C3. Membership Inference Attacks

[2026/03] Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents
[2026/01] VidLeaks: Membership Inference Attacks Against Text-to-Video Models
[2026/01] Powerful Training-Free Membership Inference Against Autoregressive Language Models
[2026/01] When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models
[2025/12] Watermarks for Embeddings-as-a-Service Large Language Models
[2025/12] Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks
[2025/12] Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models
[2025/11] GRPO Privacy Is at Risk: A Membership Inference Attack Against Reinforcement Learning With Verifiable Rewards
[2025/10] Fast-MIA: Efficient and Scalable Membership Inference for LLMs
[2025/10] Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models
[2025/10] Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
[2025/10] Membership Inference Attacks on Tokenizers of Large Language Models
[2025/09] DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
[2025/08] Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attacks
[2025/08] Membership Inference Attacks on LLM-based Recommender Systems
[2025/08] Win-k: Improved Membership Inference Attacks on Small Language Models
[2025/07] LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models
[2025/07] CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
[2025/07] Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs
[2025/06] SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation
[2025/06] Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
[2025/06] Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
[2025/06] What Really is a Member? Discrediting Membership Inference via Poisoning
[2025/06] SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
[2025/05] Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models
[2025/05] Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models
[2025/05] Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
[2025/03] Membership Inference Attacks on Large-Scale Models: A Survey
[2025/03] Privacy Auditing of Large Language Models
[2025/02] Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
[2025/02] Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
[2025/02] Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
[2025/01] Membership Inference Attacks Against Vision-Language Models
[2025/01] Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack
[2024/12] LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states
[2024/11] On the Privacy Risk of In-context Learning
[2024/11] Membership Inference Attacks against Large Vision-Language Models
[2024/10] Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models
[2024/10] Mask-based Membership Inference Attacks for Retrieval-Augmented Generation
[2024/10] PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models
[2024/10] Identity-Focused Inference and Extraction Attacks on Diffusion Models
[2024/10] Detecting Training Data of Large Language Models via Expectation Maximization
[2024/09] Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
[2024/09] Predicting and analyzing memorization within fine-tuned Large Language Models
[2024/09] Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
[2024/09] Order of Magnitude Speedups for LLM Membership Inference
[2024/09] Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
[2024/09] Membership Inference Attacks Against In-Context Learning
[2024/08] PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
[2024/08] MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector
[2024/08] Nob-MIAs: Non-biased Membership Inference Attacks Assessment on Large Language Models with Ex-Post Dataset Construction
[2024/07] Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens
[2024/06] Seeing Is Believing: Black-Box Membership Inference Attacks Against Retrieval Augmented Generation
[2024/06] Inherent Challenges of Post-Hoc Membership Inference for Large Language Models
[2024/06] Blind Baselines Beat Membership Inference Attacks for Foundation Models
[2024/06] Noisy Neighbors: Efficient membership inference attacks against LLMs
[2024/06] LLM Dataset Inference: Did you train on my dataset?
[2024/05] Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation
[2024/05] Towards Black-Box Membership Inference Attack for Diffusion Models
[2024/05] Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
[2024/04] Sampling-based Pseudo-Likelihood for Membership Inference Attacks
[2024/02] Do Membership Inference Attacks Work on Large Language Models?
[2023/12] Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
[2023/11] Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration
[2023/10] User Inference Attacks on Large Language Models
[2023/09] An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
[2023/08] White-box Membership Inference Attacks against Diffusion Models
[2023/03] Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
[2022/10] Membership Inference Attacks Against Text-to-image Generation Models