On the Interaction of Compressibility and Adversarial Robustness

• URL: http://arxiv.org/abs/2507.17725v1
• Date: Wed, 23 Jul 2025 17:35:48 GMT
• Title: On the Interaction of Compressibility and Adversarial Robustness
• Authors: Melih Barsbey, Antônio H. Ribeiro, Umut Şimşekli, Tolga Birdal,
• Abstract summary: We analyze how different forms of compressibility - such as neuron-level sparsity and spectral compressibility - affect adversarial robustness.<n>We show that these forms of compression can induce a small number of highly sensitive directions in the representation space, which adversaries can exploit.<n>Our findings show a fundamental tension between structured compressibility and robustness, and suggest new pathways for designing models that are both efficient and secure.
• Score: 15.677544432057921
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern neural networks are expected to simultaneously satisfy a host of desirable properties: accurate fitting to training data, generalization to unseen inputs, parameter and computational efficiency, and robustness to adversarial perturbations. While compressibility and robustness have each been studied extensively, a unified understanding of their interaction still remains elusive. In this work, we develop a principled framework to analyze how different forms of compressibility - such as neuron-level sparsity and spectral compressibility - affect adversarial robustness. We show that these forms of compression 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 simple yet instructive robustness bound, revealing how neuron and spectral compressibility impact $L_\infty$ and $L_2$ robustness via their effects on the learned representations. Crucially, the vulnerabilities we identify arise irrespective of how compression is achieved - whether via regularization, architectural bias, or implicit 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 perturbations. Our findings show a fundamental tension between structured compressibility and robustness, and suggest new pathways for designing models that are both efficient and secure.

Related papers

• Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity [51.40558987254471]
  Real-world applications of reinforcement learning often involve environments where agents operate on complex, high-dimensional observations. This paper addresses the question of reinforcement learning under $textitgeneral$ latent dynamics from a statistical and algorithmic perspective.
  arXiv  Detail & Related papers  (2024-10-23T14:22:49Z)
• Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data [38.44734564565478]
  We provide a theoretical understanding of adversarial examples and adversarial training algorithms from the perspective of feature learning theory.<n>We show that the adversarial training method can provably strengthen the robust feature learning and suppress the non-robust feature learning.
  arXiv  Detail & Related papers  (2024-10-11T03:59:49Z)
• Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and Efficiency [3.3490724063380215]
  Adrial training has been presented as a mitigation strategy which can result in more robust models. We explore the effects of two different model compression methods -- structured weight pruning and quantization -- on adversarial robustness. We show that adversarial fine-tuning of compressed models can achieve robustness performance comparable to adversarially trained models.
  arXiv  Detail & Related papers  (2024-03-14T14:34:25Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• Understanding Robust Overfitting from the Feature Generalization Perspective [61.770805867606796]
  Adversarial training (AT) constructs robust neural networks by incorporating adversarial perturbations into natural data. It is plagued by the issue of robust overfitting (RO), which severely damages the model's robustness. In this paper, we investigate RO from a novel feature generalization perspective.
  arXiv  Detail & Related papers  (2023-10-01T07:57:03Z)
• Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces [9.945881685938602]
  We propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models in heterogeneous data spaces. By introducing a novel causal adversarial perturbation and applying adversarial training, we create a new regularizer that combines individual fairness, causality, and robustness in the classifier.
  arXiv  Detail & Related papers  (2023-08-17T12:16:48Z)
• Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
  We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks. We present an adversarial training strategy that mitigates the impact of such simulated attacks.
  arXiv  Detail & Related papers  (2022-03-25T19:57:19Z)
• Robustness in Deep Learning for Computer Vision: Mind the gap? [13.576376492050185]
  We identify, analyze, and summarize current definitions and progress towards non-adversarial robustness in deep learning for computer vision. We find that this area of research has received disproportionately little attention relative to adversarial machine learning.
  arXiv  Detail & Related papers  (2021-12-01T16:42:38Z)
• Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception [16.60105791126744]
  We investigate how adversarial perturbations influence the internal representations of visual neural networks. We find distinct geometric signatures for each type of network, revealing different mechanisms for achieving robust representations. Our results shed light on the strategies of robust perception networks, and help explain how geometricality may be beneficial to machine and biological computation.
  arXiv  Detail & Related papers  (2021-11-12T22:59:45Z)
• Non-Singular Adversarial Robustness of Neural Networks [58.731070632586594]
  Adrial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. We formalize the notion of non-singular adversarial robustness for neural networks through the lens of joint perturbations to data inputs as well as model weights.
  arXiv  Detail & Related papers  (2021-02-23T20:59:30Z)
• Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition [133.35968094967626]
  Skeleton-based action recognition has attracted increasing attention due to its strong adaptability to dynamic circumstances. With the help of deep learning techniques, it has also witnessed substantial progress and currently achieved around 90% accuracy in benign environment. Research on the vulnerability of skeleton-based action recognition under different adversarial settings remains scant.
  arXiv  Detail & Related papers  (2020-05-14T17:12:52Z)
• Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness [97.67477497115163]
  We use mode connectivity to study the adversarial robustness of deep neural networks. Our experiments cover various types of adversarial attacks applied to different network architectures and datasets. Our results suggest that mode connectivity offers a holistic tool and practical means for evaluating and improving adversarial robustness.
  arXiv  Detail & Related papers  (2020-04-30T19:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.