Research map / Adversarial robustness and security / Attacks on text and graphs
Fooling Detection Alone is Not Enough: Adversarial Attack against Multiple Object Tracking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use tracker hijacking to fabricate a shifted detection box and mislead the tracker, rather than only erasing detections | YOLOv3 with Kalman-filter MOT · Berkeley Deep Drive; 3 attacked frames | attack success rate: up to ~25% -> 100% | Helped |
| Blindly erase target detections without steering the tracker | YOLOv3 with Kalman-filter MOT · MOT with R=60, H=6 | consecutive frames detection attack must fool: 60 frames | Hurt |
| Use tracker hijacking with a successful adversarial example on one frame | YOLOv3 with Kalman-filter MOT · Berkeley Deep Drive; cov=0.1 | attack success rate: 50% | Helped |
| Use tracker hijacking with a successful adversarial example on one frame | YOLOv3 with Kalman-filter MOT · Berkeley Deep Drive; cov=0.01 | attack success rate: 30% | Helped |
Closest papers by meaning
- SlowTrack: Increasing the Latency of Camera-Based Perception in Autonomous Driving Using Adversarial Examples (AAAI 2024 · similarity 0.86)
- Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving (CVPR 2024 · similarity 0.85)
- Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection (ICLR 2024 · similarity 0.84)
- Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework (CVPR 2025 · similarity 0.84)
- Multiple Object Tracking as ID Prediction (CVPR 2025 · similarity 0.84)
- Can't Slow Me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.