Real-World Adversarial Attack

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

13 shown of 13 papers with code (15 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Real-world adversarial attack on MTCNN face detection system
  14 Oct 2019 5 repositories listed
  Recent studies proved that deep learning approaches achieve remarkable results on face detection task.
• AdvHat: Real-world adversarial attack on ArcFace Face ID system
  23 Aug 2019 4 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 3 pointer-only (licence)
  In this paper we propose a novel easily reproducible technique to attack the best public Face ID system ArcFace in different shooting conditions.
• sudo rm -rf agentic_security
  26 Mar 2025 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Large Language Models (LLMs) are increasingly deployed as computer-use agents, autonomously performing tasks within real desktop or web environments.
• To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now
  18 Oct 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  Specifically, we investigated the adversarial robustness of DMs, assessed by adversarial prompts, when eliminating unwanted concepts, styles, and objects.
• PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification
  22 Aug 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified
  However, most backdoor attacks have to modify the neural network models through training with poisoned data and/or direct model editing, which leads to a common but false belief that backdoor attack can be easily…
• Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches
  1 Aug 2023 1 repository listed
  We introduce flying adversarial patches, where multiple images are mounted on at least one other flying robot and therefore can be placed anywhere in the field of view of a victim multirotor.
• Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks
  26 Dec 2022 1 repository listed
  Extensive experiments are conducted on the Face Recognition (FR) task, and results on four representative FR models show that our method can significantly improve the attack success rate and query efficiency.
• Ignore Previous Prompt: Attack Techniques For Language Models
  17 Nov 2022 1 repository listed Syntology ran 0 of 6 samples · 6 unverified
  Transformer-based large language models (LLMs) provide a powerful foundation for natural language tasks in large-scale customer-facing applications.
• Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection
  8 Dec 2021 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images if the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth…
• Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Model
  21 Nov 2021 1 repository listed
  In our experiments, we examined the transferability of our adversarial mask to a wide range of FR model architectures and datasets.
• Attack on practical speaker verification system using universal adversarial perturbations
  19 May 2021 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  In authentication scenarios, applications of practical speaker verification systems usually require a person to read a dynamic authentication text.
• Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target Scenes
  10 Feb 2021 1 repository listed
  We use the framework to create a patch for an everyday scene and evaluate its performance using a novel evaluation process that ensures that our results are reproducible in both the digital space and the real world.
• Taking Over the Stock Market: Adversarial Perturbations Against Algorithmic Traders
  19 Oct 2020 1 repository listed
  In this study, we present a realistic scenario in which an attacker influences algorithmic trading systems by using adversarial learning techniques to manipulate the input data stream in real time.

Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.