mlsanityData to 14 Oct 2026

R-LPIPS: An Adversarially Robust Perceptual Similarity Metric

arXiv 2307.15157 ↗First posted 27 Jul 2023cs.CV cs.LG eess.IVcited by 28

Not on the map. Why?

Abstract (arXiv)

Similarity metrics have played a significant role in computer vision to capture the underlying semantics of images. In recent years, advanced similarity metrics, such as the Learned Perceptual Image Patch Similarity (LPIPS), have emerged. These metrics leverage deep features extracted from trained neural networks and have demonstrated a remarkable ability to closely align with human perception when evaluating relative image similarity. However, it is now well-known that neural networks are susceptible to adversarial examples, i.e., small perturbations invisible to humans crafted to deliberately mislead the model. Consequently, the LPIPS metric is also sensitive to such adversarial examples. This susceptibility introduces significant security concerns, especially considering the widespread adoption of LPIPS in large-scale applications. In this paper, we propose the Robust Learned Perceptual Image Patch Similarity (R-LPIPS) metric, a new metric that leverages adversarially trained deep features. Through a comprehensive set of experiments, we demonstrate the superiority of R-LPIPS compared to the classical LPIPS metric. The code is available at https://github.com/SaraGhazanfari/R-LPIPS.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

16 of 26 references.

References · 16

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2016Adversarial examples in the physical worldcited by 1,769
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  10. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
  11. 2021A Dynamical System Perspective for Lipschitz Neural Networkscited by 60
  12. 2023A Unified Algebraic Perspective on Lipschitz Neural Networkscited by 60
4 more
  1. 2021Mind the box: l1-APGD for sparse adversarial attacks on image classifierscited by 51
  2. 2019E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensemblescited by 45
  3. 2019Theoretical evidence for adversarial robustness through randomizationcited by 33
  4. 2020Advocating for Multiple Defense Strategies against Adversarial Examplescited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 9; 2025: 9; 2026: 8.

28 papers.

Sort:

By area:

  1. 2023Adversarial Illusions in Multi-Modal Embeddingscited by 29
  2. 2024Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?cited by 21
  3. 2023LipSim: A Provably Robust Perceptual Similarity Metriccited by 15
  4. 2025Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metricscited by 10
  5. 2024EMMA: Efficient Visual Alignment in Multi-Modal LLMscited by 8
  6. 2025Augmenting Perceptual Super-Resolution via Image Quality Predictorscited by 7
  7. 2024Foundation Models Boost Low-Level Perceptual Similarity Metricscited by 6
  8. 2025Hallucination Score: Towards Mitigating Hallucinations in Generative Image Super-Resolutioncited by 6
  9. 2024Adversarial purification for no-reference image-quality metrics: applicability study and new methodscited by 5
  10. 2025DeepShade: Enable Shade Simulation by Text-conditioned Image Generationcited by 4
  11. 2024OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removalcited by 3
  12. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
16 more
  1. 2024Towards Unified Benchmark and Models for Multi-Modal Perceptual Metricscited by 2
  2. 2025Adapting to Evolving Adversaries with Regularized Continual Robust Trainingcited by 2
  3. 2025Robustness in Both Domains: CLIP Needs a Robust Text Encodercited by 2
  4. 2026Counterfactual Explanations on Robust Perceptual Geodesicscited by 2
  5. 2024Position: Towards Resilience Against Adversarial Examplescited by 1
  6. 2026BiRQA: Bidirectional Robust Quality Assessment for Imagescited by 1
  7. 2024Stochastic BIQA: Median Randomized Smoothing for Certified Blind Image Quality Assessmentcited by 0
  8. 2025Disentangling Safe and Unsafe Corruptions via Anisotropy and Localitycited by 0
  9. 2025Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devicescited by 0
  10. 2025Structured Uncertainty Similarity Score (SUSS): Learning a Probabilistic, Interpretable, Perceptual Metric Between Imagescited by 0
  11. 2026Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoorscited by 0
  12. 2026The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generationcited by 0
  13. 2026ShadeBench: A Benchmark Dataset for Building Shade Simulation in Sustainable Societycited by 0
  14. 2026Injecting Image Guidance into Text-Conditioned Diffusion Models at Inferencecited by 0
  15. 2026PlantShade: Predicting Plant Shadows for Lighting-Aware Robotic Agricultural Operationcited by 0
  16. 2026Pareto-Improving Adversarial Attacks with Primal-Dual Regularizationcited by 0