Pith. sign in

REVIEW 4 cited by

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

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 2404.11357 v2 pith:T5DQNHUP submitted 2024-04-17 cs.CV

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

Hangtao Zhang , Shengshan Hu , Yichen Wang , Leo Yu Zhang , Ziqi Zhou , Xianlong Wang , Yanjun Zhang , Chao Chen This is my paper
classification cs.CV
keywords objectbackdoordetectionattackdetectordetectorsattacksautonomous
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. Dual-branch Robust Unlearnable Examples

    cs.CV 2026-05 unverdicted novelty 7.0

    DUNE creates robust unlearnable examples through dual-branch spatial-color perturbation optimization and ensemble strategies, achieving lower average test accuracies of 14.95% to 50.82% than 12 prior methods against 7...

  2. GhostPrompt: Cross-Image Adversarial Prompt for Vision-Language Models

    cs.CR 2026-07 conditional novelty 6.0

    GhostPrompt is a universal adversarial text suffix that, after one optimization, steers VLMs to attacker-chosen outputs across diverse unseen images, reporting >30% ASR gains over prior prompt attacks.

  3. Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics

    cs.CR 2026-06 unverdicted novelty 6.0

    MTK detects jailbreaks by monitoring the evolution of prompt neighborhood structures on the data manifold through LLM layers, reporting 95% TPR at 5% FPR on benign and 2% on pseudo-malicious prompts plus 85% TPR under...

  4. Dual-branch Robust Unlearnable Examples

    cs.CV 2026-05 unverdicted novelty 5.0

    DUNE optimizes perturbations in spatial and color domains with model ensembles to produce robust unlearnable examples that reduce test accuracy to 14.95%-50.82% under 7 defenses on CIFAR-10 and ImageNet, outperforming...