The paper demonstrates that a single poisoned data point can successfully create a backdoor in linear models and ReLU neural networks without needing detailed knowledge of the training data. It establishes provable conditions under which this one‑poison attack works with high probability, achieving zero backdooring error while leaving the model’s normal performance largely unaffected. The attack relies only on coarse geometric bounds of the input space and training parameters.
By Thorsten Peinemann, Paula Arnold, Sebastian Berndt, Thomas Eisenbarth, Esfandiar Mohammadi
arXiv:2605.13214v3 Announce Type: replace-cross
Abstract: Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a cl...
By Marte Eggen, Eirik Reiestad, Kristian Gj{\o}steen, Inga Str\"umke
arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.
By Srishti Gupta, Zhang Chen, Luca Demetrio, Fabio Brau, Xiaoyi Feng, Zhaoqiang Xia, Antonio Emanuele Cin\`a, Maura Pintor, Luca Oneto, Ambra Demontis, Battista Biggio, Fabio Roli
arXiv:2506.12454v2 Announce Type: replace-cross
Abstract: What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this wor...
By Matteo Vilucchio, Lenka Zdeborov\'a, Bruno Loureiro
arXiv:2502. 02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings.
By Javier Rando, Jie Zhang, Nicholas Carlini, Florian Tram\`er
arXiv:2609.36117v1 Announce Type: new
Abstract: Securing modern AI systems against backdoor attacks remains an open challenge and requires fundamentally principled estimates of the adversary's budget...
By Issam Seddik, Mohamed El Amine Seddik
Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted.
arXiv:2510. 09288v2 Announce Type: replace-cross Abstract: The vulnerability of machine learning models to adversarial attacks remains a critical societal security challenge.
By Pablo G. Arce, Roi Naveiro, David R\'ios Insua
arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.
By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud
arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
By Paul K. Mandal, Pavan Reddy, Tristan Malatynski
arXiv:2605. 04209v2 Announce Type: replace-cross Abstract: We present Sparse Backdoor, a supply-chain attack that plants a provably undetectable backdoor in pre-trained image classifiers, including convolutional networks and Vision Transformers.
By Sarthak Choudhary, Atharv Singh Patlan, Nils Palumbo, Ashish Hooda, Kassem Fawaz, Somesh Jha
arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.
By Paul K. Mandal, Pavan Reddy, Tristan Malatynski