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:2609.15029v1 Announce Type: cross
Abstract: Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns t...
By Aashiq Muhamed, Mona T. Diab, Virginia Smith, Andrew Ilyas, Matthew Jagielski
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
The paper investigates how inference optimization for large language models can introduce numerical inconsistencies that trigger hidden backdoors. It introduces two types of optimization‑triggered backdoors: the Input‑Specific Optimization Backdoor (ISOB) and the Universal Optimization Backdoor (UOB), the latter enabling a model to remain benign under normal execution but activate a backdoor when optimization is applied. Experiments on seven open‑source LLMs, across multiple tasks and optimization backends, show UOB can achieve up to 100% attack success while maintaining clean accuracy, and the authors propose three defenses that reduce the attack success rate to 0.02.
By Yifei Wang, Yida Yang, Tianlin Li, Xiaohan Zhang, Xiaoyu Zhang, Li Pan
arXiv:2607. 05748v1 Announce Type: new Abstract: The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning.
By Qi Zhao, Christian Wressnegger
The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples.
arXiv:2606. 26285v1 Announce Type: cross Abstract: Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation.
By William Aiken, Paula Branco, Guy-Vincent Jourdan, Iosif-Viorel Onut
arXiv:2610.19766v1 Announce Type: cross
Abstract: Although Artificial Intelligence (AI)-based Intrusion Detection Systems (IDSs) are increasingly deployed in operational networks, their dependence on...
By Florian Spelter, Johannes F. Loevenich, Tobias H\"urten, Erik Adler, Maxime Schwarzer, Laurin Holz, Roberto Rigolin F. Lopes
arXiv:2608. 09577v1 Announce Type: new Abstract: Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging supply chain where a single poisoned skill can persistently compromise every agent that installs it.
By Hao Sui, Simeng Qin, Jie Liao, Xiaojun Jia, Bing Chen, Yang Liu
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. 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:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
By Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang