Unlearnable examples
PulseAugur coverage of Unlearnable examples — every cluster mentioning Unlearnable examples across labs, papers, and developer communities, ranked by signal.
-
Survey details 'adversarial attacks for good' to protect visual content
A new survey paper explores the concept of "adversarial attacks for good," where security techniques are inverted to protect visual content. The paper identifies five research areas that independently developed these pr…
-
Survey explores 'adversarial attacks for good' to protect visual content
This survey paper explores the concept of "adversarial attacks for good," where security measures are applied to visual content to prevent misuse. It examines five research areas—privacy filters, unlearnable examples, g…
-
TextCloak framework uses RL to protect text from LLM exploitation
Researchers have developed TextCloak, a new framework designed to protect textual data from unauthorized exploitation by Large Language Models (LLMs). This system utilizes reinforcement learning to transform clean text …