Image de couverture de livre

Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Dunnett, Kealan, Arablouei, Reza, Miller, Dimity, Dedeoglu, Volkan, Jurdak, Raja
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

BadDet+: Robust Backdoor Attacks for Object Detection
par: Dunnett, Kealan, et autres
Publié: (2026)

Backdoor Mitigation via Invertible Pruning Masks
par: Dunnett, Kealan, et autres
Publié: (2025)

Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies
par: Dunnett, Kealan, et autres
Publié: (2024)

Unlearning Backdoor Attacks through Gradient-Based Model Pruning
par: Dunnett, Kealan, et autres
Publié: (2024)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
par: Wei, Shaokui, et autres
Publié: (2024)

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
par: Cheng, Siyuan, et autres
Publié: (2024)

SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
par: Wang, Qiannan, et autres
Publié: (2023)

Robust Anti-Backdoor Instruction Tuning in LVLMs
par: Xun, Yuan, et autres
Publié: (2025)

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
par: Sun, Mengyuan, et autres
Publié: (2025)

PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning
par: Xu, Yukai, et autres
Publié: (2024)

CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World
par: Zhao, Shuxin, et autres
Publié: (2025)

Mitigating Backdoor Attacks using Activation-Guided Model Editing
par: Hsieh, Felix, et autres
Publié: (2024)

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
par: Li, Jiachen, et autres
Publié: (2025)

AdvART: Adversarial Art for Camouflaged Object Detection Attacks
par: Guesmi, Amira, et autres
Publié: (2023)

Backdoor Cleaning without External Guidance in MLLM Fine-tuning
par: Rong, Xuankun, et autres
Publié: (2025)

Model X-ray:Detecting Backdoored Models via Decision Boundary
par: Su, Yanghao, et autres
Publié: (2024)

Towards Physically Realizable Adversarial Attenuation Patch against SAR Object Detection
par: Zhang, Yiming, et autres
Publié: (2026)

AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
par: Lu, Jialin, et autres
Publié: (2024)

AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
par: Lu, Jialin, et autres
Publié: (2025)

We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature
par: Li, Jiachun, et autres
Publié: (2021)

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
par: Lin, Weilin, et autres
Publié: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
par: Jin, Haibo, et autres
Publié: (2021)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
par: Abad, Gorka, et autres
Publié: (2026)

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
par: Stein, Kyle, et autres
Publié: (2024)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
par: Li, Zida, et autres
Publié: (2026)

Backdoor Directions in Vision Transformers
par: Karayalcin, Sengim, et autres
Publié: (2026)

Detecting Adversarial Attacks in Semantic Segmentation via Uncertainty Estimation: A Deep Analysis
par: Maag, Kira, et autres
Publié: (2024)

Signal Adversarial Examples Generation for Signal Detection Network via White-Box Attack
par: Li, Dongyang, et autres
Publié: (2024)

Clean-image Backdoor Attacks
par: Rong, Dazhong, et autres
Publié: (2024)

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
par: Liu, Haozhe, et autres
Publié: (2024)

Advancing Security in AI Systems: A Novel Approach to Detecting Backdoors in Deep Neural Networks
par: Hossain, Khondoker Murad, et autres
Publié: (2024)

Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks
par: Unnervik, Alexander, et autres
Publié: (2024)

iBA: Backdoor Attack on 3D Point Cloud via Reconstructing Itself
par: Bian, Yuhao, et autres
Publié: (2024)

Backdooring CLIP through Concept Confusion
par: Hu, Lijie, et autres
Publié: (2025)

Revocable Backdoor for Deep Model Trading
par: Xu, Yiran, et autres
Publié: (2024)

MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World
par: Zhou, Zheng, et autres
Publié: (2023)

Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects
par: Zhou, Zirun, et autres
Publié: (2025)

Assessing Neural Network Robustness via Adversarial Pivotal Tuning
par: Christensen, Peter Ebert, et autres
Publié: (2022)

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
par: Yu, Yi, et autres
Publié: (2024)

XAI-Based Detection of Adversarial Attacks on Deepfake Detectors
par: Pinhasov, Ben, et autres
Publié: (2024)