The paper introduces PLUS, a detector‑agnostic subspace signal that enhances near‑out‑of‑distribution (near‑OOD) detection. PLUS selects the most class‑active neurons via a sparse autoencoder, orthonormalizes their decoder directions to form a low‑dimensional subspace, and scores inputs using a per‑class whitened squared Mahalanobis distance within that subspace. The resulting signal is fused additively with any calibrated base score using a single global weight, improving near‑OOD AUROC across 126 detector–backbone combinations while largely preserving far‑OOD performance.
By Wonseok Shin, Songkuk Kim
Post-hoc out-of-distribution (OOD) detection is mature on far-OOD yet remains weak on near-OOD. These two settings differ in their use of class-characteristic feature directions: far-OOD inputs largel...
arXiv:2602. 21160v3 Announce Type: replace-cross Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model's ignorance involves a benign or safety-critical class.
By Mame Diarra Toure, David A. Stephens
arXiv:2607. 23860v1 Announce Type: new Abstract: Deep ensembles provide the most reliable uncertainty estimates in deep learning, but their cost grows linearly with the number of members.
By Mihai Suteu, Ovidiu Serban
arXiv:2607. 12501v3 Announce Type: replace Abstract: The Forward-Forward algorithm trains each layer locally, so that a scalar goodness - the sum of squared activations - is high on real inputs and low on contrastive ones.
By Paolo Giannitrapani
CORE-STACK+ is a new meta‑learning framework for deep stacked generalization that tackles two key problems in heterogeneous vision ensembles: prediction‑space multicollinearity and calibration collapse. It introduces a four‑step preconditioning pipeline—kernelized redundancy filtering, a lightweight differentiable meta‑feature gate, a spectrum‑adaptive ridge penalty, and a Laplace‑approximate Bayesian blender—to jointly improve conditioning and calibration. Across six vision benchmarks, CORE‑STACK+ boosts accuracy, reduces model count and inference cost, and significantly lowers expected calibration error compared to existing methods.
By Noor Islam S. Mohammad
arXiv:2608. 01090v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are attractive for resource-constrained remote-sensing systems, but reliable out-of-distribution (OOD) detection remains challenging.
By Srinivas Anumasa, Rushi Shah, Qiran Zou, Dianbo Liu
arXiv:2610.15359v1 Announce Type: cross
Abstract: Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certif...
By Rui Zhang, Xinle Cao, Huazhen Yu, Jian Liu, Youwen Zhu
The paper investigates whether stacking multiple defenses around large language models (LLMs) truly compounds security. Using the Adversary Access‑Tier Model (AATM) and a cost‑tiering system, the authors analyze a seven‑layer defense stack and find that failure correlations between layers are consistently positive, meaning the residual attack success is higher than the multiplicative prediction. Despite high coverage and low false refusals, the stack’s performance is largely driven by common architectural causes rather than diverse, independent defenses.
By Abrar Alotaibi, Muhammad Shahid Jabbar, Sadam Al-Azani, Moataz Ahmed
A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation. Adam's per-coordinate preconditioner drifts along each symmetry orbit, which pulls the trajectory off the symmetry quotient where the optimization lives and blurs the singular-learning rate the quotient makes readable.
arXiv:2609.38901v1 Announce Type: new
Abstract: Representer explanations rank the training landmarks that most influence a self-supervised representation. At scale, this ranking rests on up to four s...
By Jayanta Mukherjee, Shourya Verma, Mengbo Wang, Jasorsi Ghosh, Ananth Grama
arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.
By Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig