mlsanityData to 7 Oct 2026

ALA: Naturalness-aware Adversarial Lightness Attack

arXiv 2201.06070 ↗First posted 16 Jan 2022cs.CV cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

Most researchers have tried to enhance the robustness of DNNs by revealing and repairing the vulnerability of DNNs with specialized adversarial examples. Parts of the attack examples have imperceptible perturbations restricted by Lp norm. However, due to their high-frequency property, the adversarial examples can be defended by denoising methods and are hard to realize in the physical world. To avoid the defects, some works have proposed unrestricted attacks to gain better robustness and practicality. It is disappointing that these examples usually look unnatural and can alert the guards. In this paper, we propose Adversarial Lightness Attack (ALA), a white-box unrestricted adversarial attack that focuses on modifying the lightness of the images. The shape and color of the samples, which are crucial to human perception, are barely influenced. To obtain adversarial examples with a high attack success rate, we propose unconstrained enhancement in terms of the light and shade relationship in images. To enhance the naturalness of images, we craft the naturalness-aware regularization according to the range and distribution of light. The effectiveness of ALA is verified on two popular datasets for different tasks (i.e., ImageNet for image classification and Places-365 for scene recognition).

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 16 Jan 2022.

Builds on

22 of 34 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2016Adversarial examples in the physical worldcited by 1,762
  10. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  11. 2019ColorFool: Semantic Adversarial Colorizationcited by 89
  12. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 56
10 more
  1. 2017Geometric robustness of deep networks: analysis and improvementcited by 45
  2. 2021AVA: Adversarial Vignetting Attack against Visual Recognitioncited by 29
  3. 2021Adversarial Relighting Against Face Recognitioncited by 16
  4. 2019Taking Care of The Discretization Problem: A Comprehensive Study of the Discretization Problem and A Black-Box Adversarial Attack in Discrete Integer Domaincited by 14
  5. 2020Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detectioncited by 14
  6. 2021Learning to Adversarially Blur Visual Object Trackingcited by 14
  7. 2019EdgeFool: An Adversarial Image Enhancement Filtercited by 10
  8. 2021AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learningcited by 9
  9. 2021ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networkscited by 7
  10. 2020Semantically Adversarial Learnable Filterscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 1; 2026: 1.

11 papers.

  1. 2023Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Modelscited by 42
  2. 2024Perception-guided Jailbreak against Text-to-Image Modelscited by 37
  3. 2024Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectorycited by 35
  4. 2023On the Robustness of Segment Anythingcited by 24
  5. 2024SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environmentscited by 22
  6. 2023Does Few-shot Learning Suffer from Backdoor Attacks?cited by 19
  7. 2024Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attackcited by 18
  8. 2024PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questionscited by 14
  9. 2024Texture Re-scalable Universal Adversarial Perturbationcited by 9
  10. 2025Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolutioncited by 3
  11. 2026TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attackscited by 0