paper-with-me

Papers

TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness

2026-05-28 · Michał Kozyra, Gesine Reinert arxiv

Modern deep networks remain fragile under distribution shift and adversarial perturbations, often due to excessive or poorly structured input sensitivity. We introduce TASER (Task-Aware Stein Regularisation), a training-time regularisation framework derived from Langevin Stein operators. By penalising pointwise Stein residuals under the training distribution, TASER encourages geometric compatibility between predictors and data density, inducing anisotropic, data-aware smoothness. We provide theoretical links between Stein regularisation and reduced first-order shift sensitivity, develop scalable implementation variants compatible with modern architectures, and demonstrate improved robustness and stability across regression and vision benchmarks. Across CIFAR-10 experiments, TASER consistently improves the adversarial robustness of established training methods without incurring statistically significant clean-accuracy degradation.

📄 PDF Abstract BibTeX arXiv:2605.30601

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering

2022-10-11 · Hao Cheng, Hao Fang, Xiaodong Liu, Jianfeng Gao

Given its effectiveness on knowledge-intensive natural language processing tasks, dense retrieval models have become increasingly popular. Specifically, the de-facto architecture for open-domain question answering uses t…

Open-Domain Question AnsweringQuestion AnsweringRetrieval

TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning

2026-03-10 · Sizhe Huang, Shujie Yang arxiv

As backdoor attacks in UAV-based decentralized federated learning (DFL) grow increasingly stealthy and sophisticated, existing defenses have likewise escalated in complexity. Yet these defenses, which rely heavily on out…

Federated LearningOutlier Detection

TASER: Translation Assessment via Systematic Evaluation and Reasoning

2025-09-30 · Monishwaran Maheswaran, Marco Carini, Christian Federmann, Tony Diaz arxiv

We introduce TASER (Translation Assessment via Systematic Evaluation and Reasoning), a metric that uses Large Reasoning Models (LRMs) for automated translation quality assessment. TASER harnesses the explicit reasoning c…

TASER: Table Agents for Schema-guided Extraction and Recommendation

2025-08-18 · Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh 외 arxiv

Real-world financial filings report critical information about an entity's investment holdings, essential for assessing that entity's risk, profitability, and relationship profile. Yet, these details are often buried in …

Table Detection

Stein transport for Bayesian inference

2024-09-02 · Nikolas Nüsken

We introduce $\textit{Stein transport}$, a novel methodology for Bayesian inference designed to efficiently push an ensemble of particles along a predefined curve of tempered probability distributions. The driving vector…

Bayesian Inference