Newest papers

ExGrad: Beyond Suppression - Explicit Clean-Gradient Subtraction in Adversarial Training

Zhiyuan Ye, Xiangyu Zhou, Ji Qi, Hao Zhang, Yi Zhou · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30018 · open-access PDF

Arabic

إن التدريب المضاد يأتي من التحديثات من خسائر المضاد، ولكن التراجع عن خسائر المصدر لا يعكس بشكل مباشر تأثير التحديث على الحدود المضادّة. نحن نقدم ExGrad (إعادة تكوين المضادّة المضادّة المضادّة)، الذي يُصنّع المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّة المضادّ

Machine translation (Meta M2M100); the English original follows.

Abstract

Adversarial training derives updates from surrogate losses, but source-loss descent does not directly characterize an update's effect on adversarial margins. We introduce ExGrad (extrapolative gradient recomposition), which constructs clean-input, adversarial-input, and adversarial-weight-perturbed (AWP) gradients. Virtual steps measure their margin responses, and a globally solvable three-variable problem selects coefficients over a bounded affine domain without nonnegativity constraints. Across affine radii on CIFAR-10, negative clean coefficients rapidly predominate and increase in magnitud

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30018, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange