# Robust Tracking against Adversarial Attacks

arXiv: https://arxiv.org/abs/2007.09919 · HTML: https://mlsanity.com/paper/2007.09919/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 28 of 28)

- [VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples](https://mlsanity.com/paper/2103.05905/) (2021)
- [VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows](https://mlsanity.com/paper/2108.05015/) (2021)
- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark](https://mlsanity.com/paper/2103.16746/) (2021)
- [Exploring Frequency Adversarial Attacks for Face Forgery Detection](https://mlsanity.com/paper/2203.15674/) (2022)
- [Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop](https://mlsanity.com/paper/2210.00933/) (2022)
- [WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking](https://mlsanity.com/paper/2201.07425/) (2022)
- [IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking](https://mlsanity.com/paper/2103.14938/) (2021)
- [SoK: On the Semantic AI Security in Autonomous Driving](https://mlsanity.com/paper/2203.05314/) (2022)
- [SiamMask: A Framework for Fast Online Object Tracking and Segmentation](https://mlsanity.com/paper/2207.02088/) (2022)
- [Stabilized Medical Image Attacks](https://mlsanity.com/paper/2103.05232/) (2021)
- [A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Tracking](https://mlsanity.com/paper/2105.02480/) (2021)
- [Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking](https://mlsanity.com/paper/2507.07483/) (2025)
- [ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language Tracking](https://mlsanity.com/paper/2508.05221/) (2025)
- [CDUPatch: Color-Driven Universal Adversarial Patch Attack for Dual-Modal Visible-Infrared Detectors](https://mlsanity.com/paper/2504.10888/) (2025)
- [A Similarity Paradigm Through Textual Regularization Without Forgetting](https://mlsanity.com/paper/2502.14376/) (2025)
- [PapMOT: Exploring Adversarial Patch Attack against Multiple Object Tracking](https://mlsanity.com/paper/2504.09361/) (2025)
- [Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers](https://mlsanity.com/paper/2406.01765/) (2024)
- [A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving](https://mlsanity.com/paper/2406.11707/) (2024)
- [TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers](https://mlsanity.com/paper/2407.03946/) (2024)
- [SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning](https://mlsanity.com/paper/2204.00734/) (2022)
- [LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks](https://mlsanity.com/paper/2404.06247/) (2024)
- [Adversarial Attacks on LiDAR-Based Tracking Across Road Users: Robustness Evaluation and Target-Aware Black-Box Method](https://mlsanity.com/paper/2410.20893/) (2024)
- [Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers](https://mlsanity.com/paper/2411.17468/) (2024)
- [GOT-Edit: Geometry-Aware Generic Object Tracking via Online Model Editing](https://mlsanity.com/paper/2602.08550/) (2026)
- [Evasive Hardware Trojan through Adversarial Power Trace](https://mlsanity.com/paper/2401.02342/) (2024)
- [Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features](https://mlsanity.com/paper/2406.19815/) (2024)
- [Adversarial Attack for RGB-Event based Visual Object Tracking](https://mlsanity.com/paper/2504.14423/) (2025)

## Abstract (arXiv)

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack and defense mainly reside in a single image. In this work, we first attempt to generate adversarial examples on top of video sequences to improve the tracking robustness against adversarial attacks. To this end, we take temporal motion into consideration when generating lightweight perturbations over the estimated tracking results frame-by-frame. On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance. On the other hand, we sequentially estimate the perturbations from input sequences and learn to eliminate their effect for performance restoration. We apply the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms. Extensive evaluations on the benchmark datasets demonstrate that our defense method not only eliminates the large performance drops caused by adversarial attacks, but also achieves additional performance gains when deep trackers are not under adversarial attacks.