DP training, inference, and privacy-preserving mechanisms
Newest first · 4 reviewed on this page
Search insteadJiechao Gao, Yuandong Pan, Jie Wang +2
Sensor-intensive environments enable many intelligent services by inferring user applications from heterogeneous data streams. However, not all applications should be exposed: users want some activities to stay private. This creates a tension between inferring applications for…
Jordi Luque, Fernando López, Aleix Sant
Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count. We show that this recipe breaks for speech large language models (speech-LLMs), when the acoustic encoder and…
Nan Yan, Yu-Qing Li, Xiong Wang +5
Federated low-rank adaptation (FedLoRA) allows multiple clients to collaboratively fine-tune large language models (LLMs) on downstream tasks without exposing their private data. To mitigate privacy leakage during aggregation, differential privacy (DP) is widely used to clip and…
Niloofar Mireshghallah, Hyunwoo Kim, Xuhui Zhou +4
Evaluates LLM privacy behavior through the lens of contextual integrity theory, finding significant mismatches between LLM norms and human privacy expectations.
Vaidehi Patil, Peter Hase, Mohit Bansal
Evaluates methods for deleting sensitive information from trained LLMs, finding current unlearning approaches insufficient against determined adversaries.
Jeffrey G. Wang, Jason Wang, Marvin Li +1
Develops precise methods for detecting and extracting training data from LLMs when white-box access is available, with implications for copyright and privacy.
Nicholas Carlini, Florian Tramer, Eric Wallace +9
Demonstrates that large language models memorize and can be prompted to emit verbatim training data, including PII, revealing significant privacy risks.