The paper introduces Targeted Active Search (TAS), a black-box attack that extracts forgotten prompts from models that have undergone unlearning. TAS first identifies forgotten entities by querying the model with canonical templates and an entity pool, then reconstructs the prompts by instantiating templates with these entities. Experiments on three unlearning methods, datasets, and large language models demonstrate that TAS can recover 100% of forgotten entities and up to 95% of prompts while using far fewer queries than naive probing.
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whet...
RAG-CT is a defense mechanism designed to protect Retrieval-Augmented Generation (RAG) systems from leaking personally identifiable information (PII). It works by detecting malicious queries through analysis of entropy and margin distributions, applying a score-based detection method. Experiments across four attack strategies and four baseline defenses on two datasets show that RAG-CT significantly reduces PII leakage while outperforming existing defenses, all without altering the underlying LLM or retriever.
arXiv:2604. 08304v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) extends large language models (LLMs) with external knowledge, but this access path also introduces security risks that existing work often conflates with inherent LLM flaws.
arXiv:2610.36295v1 Announce Type: cross Abstract: Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are v...
arXiv:2406.00083v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant information from external knowledge bases t...
arXiv:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.
arXiv:2608.29943v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...
arXiv:2510.17021v2 Announce Type: replace-cross Abstract: Large language model (LLM) unlearning is a key approach for removing undesired data, knowledge, or behaviors from pretrained models while ret...
arXiv:2607. 01276v1 Announce Type: cross Abstract: Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs.
arXiv:2604.22117v3 Announce Type: replace-cross Abstract: Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a sub...
arXiv:2605.21856v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines...
arXiv:2607. 09236v1 Announce Type: new Abstract: Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety.