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
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
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.
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
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
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
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
By Maryam Hashemzadeh, Jerry Huang, Minseon Kim, Marc-Alexandre C\^ot\'e, Sarath Chandar
arXiv:2606. 10217v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties.
By Pengrun Huang, Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri
arXiv:2606. 15810v1 Announce Type: cross Abstract: Large language models deployed as commercial APIs are vulnerable to model extraction attacks, while existing defenses either act too late or degrade utility for legitimate users.
By Yuyang Dai, Yushun Dong
arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.
By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov
As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.
arXiv:2608. 12962v1 Announce Type: new Abstract: Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models.
By Ziqi Zhao, Jialin Lu, Junjie Shan, Junyuan Zhang, Shuya Yang, Ka-Ho Chow