Metraipolis › archive › dc_db14de99858d

Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation — arXiv:2608.14594

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14594
License (as archived)
CC0-1.0
Archived
2026-10-18T19:39:41.206Z
SHA-256 of the archived text
1cbe00aea0fd7dae3c8fe91a45c66b0ab046038caf14093b97d111e7ecedc36e
Stable URL of this page
https://metraipolis.com/documento/dc_db14de99858d

How to cite

Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation — arXiv:2608.14594 — arXiv (en), https://arxiv.org/abs/2608.14594 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db14de99858d (Metraipolis archive dc_db14de99858d, sha256 1cbe00aea0fd7dae3c8fe91a45c66b0ab046038caf14093b97d111e7ecedc36e)
BibTeX
@misc{dcdb14de99858d,
  title = {Geometry Is Not Robustness: A Trajectory-Level Study of PGD Evaluation — arXiv:2608.14594},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14594},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db14de99858d; sha256 1cbe00aea0fd7dae3c8fe91a45c66b0ab046038caf14093b97d111e7ecedc36e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14594. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Projected Gradient Descent (PGD) is widely used to evaluate adversarial robustness, typically via final adversarial accuracy, which does not capture model behaviour throughout the attack. Recent work proposes trajectory-level diagnostics, such as loss evolution, gradient alignment, and steps-to-failure, for deeper insight into adversarial optimisation dynamics. However, whether these diagnostics reliably indicate robustness strength remains unclear. We conduct a trajectory-level investigation of PGD attacks on convolutional neural networks trained on Fashion-MNIST. We compare clean-trained and adversarially-trained models across multiple robustness regimes, using rigorous 20-step PGD evaluations with random initialisation and multiple restarts for robustness measurement, and single-initialisation trajectory recording for diagnostics. We record full PGD trajectories across 3000 clean-correct samples per model and analyse loss evolution, gradient alignment, and failure timing across attack iterations. Our results reveal a clear robustness hierarchy across models; however, trajectory metrics do not contribute equally to its identification. Mean loss trajectories and gradient alignment patterns appear quantitatively similar across adversarially-trained models with substantially different robust accuracies. In contrast, steps-to-failure distributions provide a clearer separation of robustness regimes, directly reflecting functional resistance to adversarial perturbation. These findings indicate that trajectory-level diagnostics describe optimisation geometry but do not independently measure adversarial robustness. Their interpretability depends on robustness regime, attack strength, and multi-metric evaluation. Trajectory-level analysis should be a complementary diagnostic tool, interpreted in context, rather than a replacement for standard robustness measurements.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.14594 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T19:02:44.017Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).