CORTEXA
← Browse
arxivcs.LGcs.CRstat.ML2026-07-10

Statistically Undetectable Backdoors in Deep Neural Networks

Andrej Bogdanov, Alon Rosen, Neekon Vafa

We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given the full descriptions of the models (e.g., all of the weights). The backdoor provides access to invariance-based adversarial examples for every input, mapping distant inputs to unusually close outputs. However, without the backdoor, it is provably impossible (under standard cryptographic assumptions) to generate any such adversarial examples in polynomial time. Our theoretical and preliminary empirical findings demonstrate a fundamental power asymmetry between model trainers and model users.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CRcs.CVstat.ML2026-07-23

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

Vishnu Bindu Balachandran

Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized Pólya urn, we prove almost-sure convergence to a mean-field equilibrium whose s…

View free PDFSource page
arxivcs.LGcs.AIstat.ML2026-07-23

Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks

Hossein Mobahi, Peter L. Bartlett

Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge. However, standard compression heuristics of…

View free PDFSource page
arxivcs.LGcs.SIstat.ML2026-07-24

Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

Rachid Caich, Yassine Abbahaddou

Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore…

View free PDFSource page