The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.
By Thibaud Gloaguen, Mark Vero, Robin Staab, Martin Vechev
arXiv:2606. 04929v1 Announce Type: new Abstract: LLM post-training proceeds through multiple stages, e.
By Jack Sanderson, Yihan Wang, Xiaoqian Lu, Gautam Kamath, Yiwei Lu
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
arXiv:2405.18540v3 Announce Type: replace-cross
Abstract: Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of larg...
By Seanie Lee, Minsu Kim, Lynn Cherif, David Dobre, Juho Lee, Sung Ju Hwang, Kenji Kawaguchi, Gauthier Gidel, Yoshua Bengio, Esmeralda S. Whitammer, Moksh Jain
The paper introduces Quarantined Expert Shutdown (QES), a new backdoor containment strategy for large language models. QES allows backdoor learning to occur during training but routes it into a designated, quarantined expert that can be disabled at deployment. The method achieves significant reductions in attack success rates while largely preserving model utility.
By Jianwei Li, Min-Seon Kim, Jung-Eun Kim
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
arXiv:2608. 07274v1 Announce Type: cross Abstract: Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead.
By Yuhan Xie, Jingrong Huang, Chen Lyu
arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.
By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a
SynGhost is a novel task‑agnostic backdoor attack that injects invisible syntactic backdoors into pre‑training corpora of language models. It uses an entropy‑based poisoning filter, contrastive learning to select optimal targets, and an awareness module to reduce interference between backdoors, thereby preserving the model’s pre‑training performance. Experiments demonstrate that SynGhost can transfer to multiple downstream tasks and withstand several defense mechanisms such as perplexity checks, fine‑pruning, and the maxEntropy filter.
By Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu
arXiv:2608. 00732v1 Announce Type: new Abstract: Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data poisoning.
By Zixuan Zhu, Rui Wang, Lihua Jing, Jinwen Zhong
arXiv:2606. 17110v1 Announce Type: cross Abstract: Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets.
By Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree, Ihsen Alouani, Nael Abu-Ghazaleh
arXiv:2602. 04899v2 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out.
By Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade, Mary Phuong