conftrace_

privacy leakage

105 papers

Explore in graph

Co-occurring keywords

large language model (13587) membership inference (114) federated learning (1333) differential privacy (1016) adversarial attack (1621) language model (4599) membership inference attack (93) privacy preservation (380) privacy attack (119) personally identifiable information (33)

Papers

Protecting Split Learning by Potential Energy Loss IJCAI 2024
Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought IJCAI 2024
Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach NIPS 2024
Practical Privacy-Preserving MLaaS: When Compressive Sensing Meets Generative Networks AAAI 2024
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG) ACL 2024
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation NIPS 2024
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NIPS 2024
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action NIPS 2024
PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models ACL 2024
Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining NIPS 2024
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NIPS 2024
Measuring Dejavu Memorization Efficiently NIPS 2024
Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective AAAI 2024
PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques NIPS 2024
Analysis of Privacy Leakage in Federated Large Language Models AISTATS 2024
Integer Is Enough: When Vertical Federated Learning Meets Rounding AAAI 2024
Chronic Poisoning: Backdoor Attack against Split Learning AAAI 2024
ERASER: AdvERsArial Sensitive Element Remover for Image Privacy Preservation AAAI 2023
Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks (Student Abstract) AAAI 2023
ProPILE: Probing Privacy Leakage in Large Language Models NIPS 2023
Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe ACL 2023
ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation ACL 2023
Privacy Implications of Retrieval-Based Language Models EMNLP 2023
Text Embeddings Reveal (Almost) As Much As Text EMNLP 2023