arXiv Machine Learning August 19, 2026 By Roman Maksimov, Vladimir Aletov, Vladimir Solodkin, Dmitry Bylinkin, Daniil Medyakov, Aleksandr Beznosikov

Leveraging Association Context Retrieval in Knowledge Edit- ing to Build White-Box Attacks on LLMs

Read the original on arXiv Machine Learning →

The paper introduces a new white‑box attack on large language models that builds on knowledge‑editing techniques. By retrieving associative knowledge from the model, the attack extends constraint removal to a whole thematic category rather than just a predefined set of prompts. Experiments across different architectures show that this method improves attack effectiveness while preserving overall model performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Sep 25

The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning

The paper investigates how tokenization can undermine post‑release guarantees that sensitive knowledge has been edited or unlearned from open‑weight large language models. By showing that alternative valid tokenizations can bypass localized modifications, the authors introduce Toketive, a reference‑free attack that detects modified knowledge and reconstructs pre‑edit responses using only the released model. Experiments on five LLMs, six datasets, and six editing techniques reveal that 38.6% of alternative tokenizations recover suppressed information, with Toketive achieving high detection and reconstruction accuracy.

By Manit Baser, Aditya Nawal, Dinil Mon Divakaran, Mohan Gurusamy

llms nlp safety

arXiv Machine Learning

Jun 25

Exposing the Illusion of Erasure in Knowledge Editing for LLMs

arXiv:2606. 23276v2 Announce Type: replace Abstract: Knowledge Editing (KE) has emerged as a frontier for updating specific facts in LLMs without costly retraining, but its reliability and underlying mechanisms remain poorly understood.

By Advik Raj Basani, Anshuman Chhabra

llms safety

Hugging Face Trending Papers

Jun 2

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs

Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown backdoors may exist in a model.

llms safety

arXiv AI

Sep 30

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

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...

By Jiaqi Xue, Mengxin Zheng, Yebowen Hu, Fei Liu, Xun Chen, Qian Lou

llms rag robotics safety

arXiv AI

Jun 18

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

arXiv:2606. 18310v1 Announce Type: cross Abstract: Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation, posing a serious security threat for AI applications.

By Xinru Liu, Xianglong Zhang, Di Cai, Zhumin Chen, Pengfei Hu, Xin Xin

llms rag robotics benchmarks

arXiv AI

Jun 6

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

arXiv:2509. 20324v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) is an emerging approach in natural language processing that combines large language models (LLMs) with external document retrieval to produce more accurate and grounded responses.

By Atousa Arzanipour, Rouzbeh Behnia, Reza Ebrahimi, Kaushik Dutta

llms rag nlp safety

One email a morning, machine-written

Related stories

The Tokens Remember: When Tokenization Bypasses Knowledge Editing and Unlearning

Exposing the Illusion of Erasure in Knowledge Editing for LLMs

Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs

BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models

Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface