RLAA is a localized adversarial anonymization framework that adds an arbitrator to filter ghost leaks and enforce rational early stopping, yielding superior privacy-utility trade-offs on benchmarks compared to greedy baselines.
Identifying and mitigating privacy risks stemming from language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
The work proposes and evaluates techniques to reduce PII exposure from image context in online vision-language models while preserving utility for downstream applications.
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
citing papers explorer
-
Look Twice before You Leap: A Rational Framework for Localized Adversarial Anonymization
RLAA is a localized adversarial anonymization framework that adds an arbitrator to filter ghost leaks and enforce rational early stopping, yielding superior privacy-utility trade-offs on benchmarks compared to greedy baselines.
-
Assessing Privacy Preservation and Utility in Online Vision-Language Models
The work proposes and evaluates techniques to reduce PII exposure from image context in online vision-language models while preserving utility for downstream applications.
-
A Survey on the Memory Mechanism of Large Language Model based Agents
A systematic review of memory designs, evaluation methods, applications, limitations, and future directions for LLM-based agents.
- LLM Harms: A Taxonomy and Discussion