Attackers can extract private data by querying language models ^84%

Truth rate: 84%

Pros: 0
Cons: 0

Attackers can extract private data by querying language models

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: 19281

Related:

Complex queries require powerful query languages to analyze big data ^86%

86%

Data science extracts knowledge from data ^80%

80%

Data science extracts knowledge from data

Complex data models require massive big data sets ^91%

91%

Risk of data breaches and cyber attacks in big data storage ^49%

49%

Cyber attackers may use breached data for future attacks ^80%

80%

Data analytics plays a crucial role in extracting insights from big data ^89%

89%

Complexity of data models obscures insights ^89%

89%

Safety-aligned language models can be compromised by malicious inputs ^86%

86%

Safety-aligned language models can be compromised by malicious inputs

Simple prompts can reveal system instructions in language models ^87%

87%

Simple prompts can reveal system instructions in language models

Few mobile apps respect users' private data ^85%

85%