arXiv Machine Learning September 10, 2026 By Marte Eggen, Eirik Reiestad, Kristian Gj{\o}steen, Inga Str\"umke

Backdoor Channels Hidden in Latent Space: Extending Cryptographic Undetectability to Modern Neural Networks

Read the original on arXiv Machine Learning →

The Flow has not summarised this story yet — read it at arXiv Machine Learning.

arXiv Machine Learning

Jul 13

Statistically Undetectable Backdoors in Deep Neural Networks

arXiv:2607. 09532v1 Announce Type: new Abstract: We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks.

By Andrej Bogdanov, Alon Rosen, Neekon Vafa

safety

arXiv Machine Learning

Aug 6

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

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

llms multimodal safety

arXiv AI

Aug 18

Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets

arXiv:2607. 05516v2 Announce Type: replace-cross Abstract: Model-specific adversarial attacks have been extensively studied.

By Paul K. Mandal, Pavan Reddy, Tristan Malatynski

safety

arXiv AI

Jul 8

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

arXiv:2607. 05516v1 Announce Type: cross Abstract: Model-specific adversarial attacks have been extensively studied.

By Paul K. Mandal, Pavan Reddy, Tristan Malatynski

safety

Hugging Face Trending Papers

Jul 6

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

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.

safety

arXiv Machine Learning

Jun 9

Cryptographic Backdoor for Neural Networks: Boon and Bane

arXiv:2509. 20714v2 Announce Type: replace-cross Abstract: In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well.

By Anh Tu Ngo, Anupam Chattopadhyay, Subhamoy Maitra

benchmarks safety

One email a morning, machine-written

Related stories

Statistically Undetectable Backdoors in Deep Neural Networks

One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIP

Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets

Cryptographic Backdoor for Neural Networks: Boon and Bane