On the Interaction of Compressibility and Adversarial Robustness

Melih Barsbey, Antônio H. Ribeiro, Umut Simsekli, Tolga Birdal

Keywords: compressibility, compression, adversarial robustness, generalization, safety

TL;DR: We show that training methods that induce structured compressibility are likely to produce adversarial vulnerability.

Abstract: As demands for resource efficiency and safety in modern neural networks intensify, substantial research effort has gone into model compression and adversarial robustness. Yet despite progress on each in isolation, a systematic understanding of how compressibility shapes robustness remains elusive. In this paper, we develop a principled framework to analyze how different forms of structured compressibility - such as neuron-level and spectral compressibility - affect adversarial robustness. We show that structured compressibility can induce a small number of highly sensitive directions in the representation space, which adversaries can exploit to construct effective perturbations. Our analysis yields a robustness bound that reveals how neuron and spectral compressibility impact $\ell_\infty$ and $\ell_2$ robustness via their effects on the learned representations. Crucially, the vulnerabilities we identify arise irrespective of how compressibility is achieved - whether via regularization, architectural bias, or learning dynamics. Through empirical evaluations across synthetic and realistic tasks, we confirm our theoretical predictions, and further demonstrate that these vulnerabilities persist under adversarial training and transfer learning, and contribute to the emergence of universal adversarial examples. Our findings show a fundamental tension between structured compressibility and robustness and highlight new pathways for designing models that are efficient and safe.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 11954