ResearchTrend.AI
  • Communities
  • Connect sessions
  • AI calendar
  • Organizations
  • Join Slack
  • Contact Sales
Papers
Communities
Social Events
Terms and Conditions
Pricing
Contact Sales
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2026 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2505.03646
306
0
v1v2v3v4 (latest)

GRILL: Restoring Gradient Signal in Ill-Conditioned Layers for More Effective Adversarial Attacks on Autoencoders

6 May 2025
Chethan Krishnamurthy Ramanaik
Arjun Roy
Tobias Callies
Eirini Ntoutsi
    AAML
ArXiv (abs)PDFHTMLGithub
Main:7 Pages
19 Figures
Bibliography:2 Pages
3 Tables
Appendix:10 Pages
Abstract

Adversarial robustness of deep autoencoders (AEs) has received less attention than that of discriminative models, although their compressed latent representations induce ill-conditioned mappings that can amplify small input perturbations and destabilize reconstructions. Existing white-box attacks for AEs, which optimize norm-bounded adversarial perturbations to maximize output damage, often stop at suboptimal attacks. We observe that this limitation stems from vanishing adversarial loss gradients during backpropagation through ill-conditioned layers, caused by near-zero singular values in their Jacobians. To address this issue, we introduce GRILL, a technique that locally restores gradient signals in ill-conditioned layers, enabling more effective norm-bounded attacks. Through extensive experiments across multiple AE architectures, considering both sample-specific and universal attacks under both standard and adaptive attack settings, we show that GRILL significantly increases attack effectiveness, leading to a more rigorous evaluation of AE robustness. Beyond AEs, we provide empirical evidence that modern multimodal architectures with encoder-decoder structures exhibit similar vulnerabilities under GRILL.

View on arXiv
Comments on this paper