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:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.
By Paul K. Mandal, Pavan Reddy, Tristan Malatynski
arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.
By Paul K. Mandal, Pavan Reddy, Tristan Malatynski
arXiv:2507. 05113v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model.
By Binyan Xu, Fan Yang, Xilin Dai, Di Tang, Kehuan Zhang
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. 31309v1 Announce Type: cross Abstract: While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.
By Zhengxing Li, David J. Miller, Guangmingmei Yang, George Kesidis
arXiv:2505. 19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks.
By Binyan Xu, Xilin Dai, Di Tang, Kehuan Zhang
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.
Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution. Existing defenses report near-zero attack success rate on static benchmarks, yet recent adaptive evaluations show that these results collapse once the attacker is allowed to optimize against the deployed defense.
arXiv:2609.31558v1 Announce Type: new
Abstract: Contrastive Language--Image Pretraining (CLIP) has emerged as a dominant vision backbone due to its strong transferability and zero-shot capabilities....
By Ahmed Abdelnaby, Mohamed Elmahallawy
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:2510. 11709v2 Announce Type: replace-cross Abstract: Why do adversarial examples exist, and why do they transfer between models?
By Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal