Pith. sign in

REVIEW 4 cited by

Robust Adversarial Perturbation on Deep Proposal-based Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1809.05962 v2 pith:N5YFJR4Z submitted 2018-09-16 cs.CV

Yuezun Li , Daniel Tian , Ming-Ching Chang , Xiao Bian , Siwei Lyu This is my paper · ORCID
classification cs.CV
keywords adversarialalgorithmsdeeplossmethodattackingdetectorsinstance
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms. In this paper, we describe a robust adversarial perturbation (R-AP) method to attack deep proposal-based object detectors and instance segmentation algorithms. Our method focuses on attacking the common component in these algorithms, namely Region Proposal Network (RPN), to universally degrade their performance in a black-box fashion. To do so, we design a loss function that combines a label loss and a novel shape loss, and optimize it with respect to image using a gradient based iterative algorithm. Evaluations are performed on the MS COCO 2014 dataset for the adversarial attacking of 6 state-of-the-art object detectors and 2 instance segmentation algorithms. Experimental results demonstrate the efficacy of the proposed method.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Corrupting Attention: Evasion-Based Adversarial Attacks on Encoder Attention in Detection Transformers

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Optimizing a bounded l-infinity perturbation against encoder attention collapses DETR and DINO object detection to near-zero mAP, outperforming prior attacks.

  2. NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

    cs.CV 2024-12 conditional novelty 6.0 of 10

    NumbOD attacks object detectors with a spatial loss that collapses predicted boxes toward the corner and a frequency loss that amplifies high-frequency differences, reducing mAP50 to below 5.5 on all nine tested models.

  3. Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices

    cs.CV 2024-12 conditional novelty 5.0 of 10

    A background-attentive, hardware-aware adversarial training method restores real-time object detection FPS under latency attacks on edge, desktop, and cloud GPUs.

  4. Adversarial Patch Attack for Ship Detection via Localized Augmentation

    cs.CV 2025-08 conditional novelty 4.0 of 10

    Localized augmentation, applying transformations only to target ship regions, modestly improves adversarial patch attack success and transferability on YOLOv5 detectors, but results vary by model size.

Pith tools