
pgm-attack
Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.
adversarial-attackai-securitymachine-learning+1
1

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

Jailbreak vulnerability across early-exit depths LLMs. Published at NeurIPS 2026 in the FLMSec workshop

Research pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…