← all papers · overview

Forcing Generative Models To Degenerate Ones: The Power Of Data Poisoning Attacks

Abstract

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs through poisoning attacks aimed at generating undesirable outputs. While poisoning attacks have received significant attention in the image domain (e.g., object de

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).