SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples

• URL: http://arxiv.org/abs/2507.07776v2
• Date: Mon, 14 Jul 2025 15:01:42 GMT
• Title: SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples
• Authors: Dren Fazlija, Monty-Maximilian Zühlke, Johanna Schrader, Arkadij Orlov, Clara Stein, Iyiola E. Olatunji, Daniel Kudenko,
• Abstract summary: Unrestricted adversarial attacks aim to fool computer vision models without being constrained by $ell_p$-norm bounds to remain imperceptible to humans.<n>This allows attackers to circumvent traditional, norm-bounded defense strategies such as adversarial training or certified defense strategies.<n>We introduce SCOOTER - an open-source, statistically powered framework for evaluating unrestricted adversarial examples.
• Score: 2.7641556116998656
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unrestricted adversarial attacks aim to fool computer vision models without being constrained by $\ell_p$-norm bounds to remain imperceptible to humans, for example, by changing an object's color. This allows attackers to circumvent traditional, norm-bounded defense strategies such as adversarial training or certified defense strategies. However, due to their unrestricted nature, there are also no guarantees of norm-based imperceptibility, necessitating human evaluations to verify just how authentic these adversarial examples look. While some related work assesses this vital quality of adversarial attacks, none provide statistically significant insights. This issue necessitates a unified framework that supports and streamlines such an assessment for evaluating and comparing unrestricted attacks. To close this gap, we introduce SCOOTER - an open-source, statistically powered framework for evaluating unrestricted adversarial examples. Our contributions are: $(i)$ best-practice guidelines for crowd-study power, compensation, and Likert equivalence bounds to measure imperceptibility; $(ii)$ the first large-scale human vs. model comparison across 346 human participants showing that three color-space attacks and three diffusion-based attacks fail to produce imperceptible images. Furthermore, we found that GPT-4o can serve as a preliminary test for imperceptibility, but it only consistently detects adversarial examples for four out of six tested attacks; $(iii)$ open-source software tools, including a browser-based task template to collect annotations and analysis scripts in Python and R; $(iv)$ an ImageNet-derived benchmark dataset containing 3K real images, 7K adversarial examples, and over 34K human ratings. Our findings demonstrate that automated vision systems do not align with human perception, reinforcing the need for a ground-truth SCOOTER benchmark.

Related papers

• How stealthy is stealthy? Studying the Efficacy of Black-Box Adversarial Attacks in the Real World [1.799933345199395]
  This study investigates black-box adversarial attacks in computer vision.<n>We propose ECLIPSE, a novel attack method employing Gaussian blurring on sampled gradients and a local surrogate model.
  arXiv  Detail & Related papers  (2025-06-03T08:56:37Z)
• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples [8.483679748399036]
  adversarial examples threaten the safety of AI-based systems such as autonomous vehicles. In the image domain, they represent maliciously perturbed data points that look benign to humans. We propose SCOOTER - an evaluation framework for unrestricted image-based attacks.
  arXiv  Detail & Related papers  (2024-04-19T06:42:01Z)
• BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack [22.408968332454062]
  We study the unique, less-well understood problem of generating sparse adversarial samples simply by observing the score-based replies to model queries. We develop the BruSLeAttack-a new, faster (more query-efficient) algorithm for the problem. Our work facilitates faster evaluation of model vulnerabilities and raises our vigilance on the safety, security and reliability of deployed systems.
  arXiv  Detail & Related papers  (2024-04-08T08:59:26Z)
• Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks [18.66548052614702]
  We propose an adversarial training framework that uses limited human adversarial examples to generate more useful adversarial examples at scale. We demonstrate the advantages of this system on the ANLI and hate speech detection benchmark datasets.
  arXiv  Detail & Related papers  (2023-10-25T19:51:37Z)
• The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attacks [91.56314751983133]
  $A5$ is a framework to craft a defensive perturbation to guarantee that any attack towards the input in hand will fail. We show effective on-the-fly defensive augmentation with a robustifier network that ignores the ground truth label. We also show how to apply $A5$ to create certifiably robust physical objects.
  arXiv  Detail & Related papers  (2023-05-23T16:07:58Z)
• A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks [72.7373468905418]
  We develop an open-source toolkit OpenBackdoor to foster the implementations and evaluations of textual backdoor learning. We also propose CUBE, a simple yet strong clustering-based defense baseline.
  arXiv  Detail & Related papers  (2022-06-17T02:29:23Z)
• Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack [96.50202709922698]
  A practical evaluation method should be convenient (i.e., parameter-free), efficient (i.e., fewer iterations) and reliable. We propose a parameter-free Adaptive Auto Attack (A$3$) evaluation method which addresses the efficiency and reliability in a test-time-training fashion.
  arXiv  Detail & Related papers  (2022-03-10T04:53:54Z)
• Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning [95.60856995067083]
  This work is among the first to perform adversarial defense for ASV without knowing the specific attack algorithms. We propose to perform adversarial defense from two perspectives: 1) adversarial perturbation purification and 2) adversarial perturbation detection. Experimental results show that our detection module effectively shields the ASV by detecting adversarial samples with an accuracy of around 80%.
  arXiv  Detail & Related papers  (2021-06-01T07:10:54Z)
• Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting [61.99564267735242]
  Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Recent studies have demonstrated that deep neural network (DNN) methods are vulnerable to adversarial attacks. We propose a robust attack strategy called Adversarial Patch Attack with Momentum to evaluate the robustness of crowd counting models.
  arXiv  Detail & Related papers  (2021-04-22T05:10:55Z)
• Generating Unrestricted Adversarial Examples via Three Parameters [11.325135016306165]
  A proposed adversarial attack generates an unrestricted adversarial example with a limited number of parameters. It obtains an average success rate of 93.5% in terms of human evaluation on the MNIST and SVHN datasets. It also reduces the model accuracy by an average of 73% on six datasets.
  arXiv  Detail & Related papers  (2021-03-13T07:20:14Z)
• Perceptual Adversarial Robustness: Defense Against Unseen Threat Models [58.47179090632039]
  A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception. Under the neural perceptual threat model, we develop novel perceptual adversarial attacks and defenses. Because the NPTM is very broad, we find that Perceptual Adrial Training (PAT) against a perceptual attack gives robustness against many other types of adversarial attacks.
  arXiv  Detail & Related papers  (2020-06-22T22:40:46Z)

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.