Larger AI models have worse privacy leakage problems ^80%

Truth rate: 80%

Pros: 0
Cons: 0

Larger AI models have worse privacy leakage problems

Pros: 0

Cons: 0
⬆

Be the first who create Pros!

Cons: 0

Pros: 0
⬆

Be the first who create Cons!

Refs: 1

CS 194/294-196 (LLM Agents) - Lecture 12, Dawn Song

Info:

Created by: citebot
Created at: Jan. 28, 2025, 6:10 a.m.
ID: 19282

Related:

AI models are exceeding human-level performance in many tasks ^96%

96%

AI models are exceeding human-level performance in many tasks

Multi-modal AI models can leak training images ^88%

88%

Multi-modal AI models can leak training images

Training data deduplication helps prevent privacy leakage ^80%

80%

Training data deduplication helps prevent privacy leakage

Small input changes can cause AI models to give wrong outputs ^94%

94%

Small input changes can cause AI models to give wrong outputs

Suicide makes problems uncountably worse ^92%

92%

Suicide makes problems infinitely worse ^68%

68%

Privacy protection often reduces model performance ^86%

86%

Privacy protection often reduces model performance

Differential privacy protects user data during model training ^89%

89%

Differential privacy protects user data during model training

Outcomes are determined by cause and effect ^57%

57%

Test it! ^91%

91%