Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales

Terms and Conditions

Twitter GitHub LinkedIn Bluesky Youtube

© 2026 ResearchTrend.AI, All rights reserved.

Home
Papers
2104.02361
Cited By

Backdoor Attack in the Physical World

v1v2 (latest)

Backdoor Attack in the Physical World

6 April 2021

ArXiv (abs)PDF HTML

Papers citing "Backdoor Attack in the Physical World"

50 / 76 papers shown

TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening

TED++: Submanifold-Aware Backdoor Detection via Layerwise Tubular-Neighbourhood Screening

133

0

0

16 Oct 2025

Rounding-Guided Backdoor Injection in Deep Learning Model Quantization

Rounding-Guided Backdoor Injection in Deep Learning Model Quantization

Xiangxiang Chen

130

0

0

05 Oct 2025

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

122

1

0

28 Sep 2025

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS

122

0

0

05 Aug 2025

DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective

DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective

247

7

0

08 Jul 2025

FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition

FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition

353

1

0

17 May 2025

GaussTrap: Stealthy Poisoning Attacks on 3D Gaussian Splatting for Targeted Scene Confusion

GaussTrap: Stealthy Poisoning Attacks on 3D Gaussian Splatting for Targeted Scene Confusion

911

0

0

29 Apr 2025

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets

Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream DatasetsIEEE Symposium on Security and Privacy (S&P), 2025

201

2

0

16 Apr 2025

Defending Deep Neural Networks against Backdoor Attacks via Module Switching

Defending Deep Neural Networks against Backdoor Attacks via Module Switching

306

0

0

08 Apr 2025

Backdooring CLIP through Concept Confusion

Backdooring CLIP through Concept Confusion

326

1

0

12 Mar 2025

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming

REFINE: Inversion-Free Backdoor Defense via Model ReprogrammingInternational Conference on Learning Representations (ICLR), 2025

239

15

0

22 Feb 2025

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationKnowledge Discovery and Data Mining (KDD), 2024

384

2

0

17 Nov 2024

ProP: Efficient Backdoor Detection via Propagation Perturbation for
Overparametrized Models

ProP: Efficient Backdoor Detection via Propagation Perturbation for Overparametrized Models

203

0

0

11 Nov 2024

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained
Models via Model Editing

Backdoor in Seconds: Unlocking Vulnerabilities in Large Pre-trained Models via Model Editing

Thomas Hartvigsen

371

4

0

23 Oct 2024

Backdoor Attack on Vertical Federated Graph Neural Network Learning

Backdoor Attack on Vertical Federated Graph Neural Network LearningInternational Joint Conference on Artificial Intelligence (IJCAI), 2024

914

1

0

15 Oct 2024

Mitigating Backdoor Threats to Large Language Models: Advancement and
Challenges

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges

Qin Liu

Chaowei Xiao

Muhao Chen

273

11

0

30 Sep 2024

Persistent Backdoor Attacks in Continual Learning

Persistent Backdoor Attacks in Continual Learning

350

7

0

20 Sep 2024

VFLIP: A Backdoor Defense for Vertical Federated Learning via
Identification and Purification

VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and PurificationEuropean Symposium on Research in Computer Security (ESORICS), 2024

273

8

0

28 Aug 2024

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers

Camilo A. Mart´ınez-Mej´ıa

191

0

0

30 Jul 2024

Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation
for Embedding Undetectable Vulnerabilities on Speech Recognition

Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition

323

4

0

16 Jun 2024

DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person
Re-Identification in Real-World

DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World

Dongsheng Li

254

2

0

30 May 2024

A Stealthy Backdoor Attack for Without-Label-Sharing Split Learning

A Stealthy Backdoor Attack for Without-Label-Sharing Split Learning

Yuwen Pu

66

0

0

21 May 2024

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data

Mellivora Capensis: A Backdoor-Free Training Framework on the Poisoned Dataset without Auxiliary Data

116

0

0

21 May 2024

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling
Consistency

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling ConsistencyInternational Conference on Machine Learning (ICML), 2024

332

37

0

16 May 2024

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the
Physical World

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World

Lichao Sun

158

11

0

30 Apr 2024

Dual Model Replacement:invisible Multi-target Backdoor Attack based on
Federal Learning

Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning

135

5

0

22 Apr 2024

Invisible Backdoor Attack Through Singular Value Decomposition

Invisible Backdoor Attack Through Singular Value DecompositionChinese Conference on Pattern Recognition and Computer Vision (CPRCV), 2024

253

2

0

18 Mar 2024

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in
Deep Learning

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning

H. M. Dolatabadi

Christopher Leckie

196

0

0

17 Feb 2024

Test-Time Backdoor Attacks on Multimodal Large Language Models

Test-Time Backdoor Attacks on Multimodal Large Language Models

386

37

0

13 Feb 2024

The last Dance : Robust backdoor attack via diffusion models and
bayesian approach

The last Dance : Robust backdoor attack via diffusion models and bayesian approach

611

4

0

05 Feb 2024

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense
with Backdoor Exclusivity Lifting

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity LiftingIEEE Symposium on Security and Privacy (S&P), 2023

288

7

0

08 Dec 2023

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute TriggerIEEE Transactions on Dependable and Secure Computing (IEEE TDSC), 2023

Tao Wei

389

5

0

03 Dec 2023

A Unified Hardware-based Threat Detector for AI Accelerators

A Unified Hardware-based Threat Detector for AI Accelerators

212

2

0

28 Nov 2023

Domain Watermark: Effective and Harmless Dataset Copyright Protection is
Closed at Hand

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at HandNeural Information Processing Systems (NeurIPS), 2023

Heng-Chiao Huang

349

83

0

09 Oct 2023

Physical Invisible Backdoor Based on Camera Imaging

Physical Invisible Backdoor Based on Camera ImagingACM Multimedia (ACM MM), 2023

218

3

0

14 Sep 2023

Towards Robust Model Watermark via Reducing Parametric Vulnerability

Towards Robust Model Watermark via Reducing Parametric VulnerabilityIEEE International Conference on Computer Vision (ICCV), 2023

187

18

0

09 Sep 2023

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input
Detection

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input DetectionInternational Conference on Learning Representations (ICLR), 2023

Jiachen T. Wang

205

13

0

23 Aug 2023

PatchBackdoor: Backdoor Attack against Deep Neural Networks without
Model Modification

PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model ModificationACM Multimedia (ACM MM), 2023

98

11

0

22 Aug 2023

Towards Stealthy Backdoor Attacks against Speech Recognition via
Elements of Sound

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of SoundIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023

Pengcheng Zhang

Stefanos Koffas

341

48

0

17 Jul 2023

Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and
Compatible Triggers

Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers

Hongrui Chen

380

13

0

01 Jun 2023

Backdoor Attack with Sparse and Invisible Trigger

Backdoor Attack with Sparse and Invisible TriggerIEEE Transactions on Information Forensics and Security (IEEE TIFS), 2023

318

35

0

11 May 2023

Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

320

10

0

27 Mar 2023

Backdoor Defense via Adaptively Splitting Poisoned Dataset

Backdoor Defense via Adaptively Splitting Poisoned DatasetComputer Vision and Pattern Recognition (CVPR), 2023

Kuofeng Gao

Jindong Gu

Yong-Liang Yang

183

70

0

23 Mar 2023

Black-box Backdoor Defense via Zero-shot Image Purification

Black-box Backdoor Defense via Zero-shot Image PurificationNeural Information Processing Systems (NeurIPS), 2023

Ninghao Liu

283

40

0

21 Mar 2023

SATBA: An Invisible Backdoor Attack Based On Spatial Attention

SATBA: An Invisible Backdoor Attack Based On Spatial AttentionInternational Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), 2023

Xiaowei Xu

Leon Bevan Bullock

191

2

0

25 Feb 2023

Defending Against Backdoor Attacks by Layer-wise Feature Analysis

Defending Against Backdoor Attacks by Layer-wise Feature AnalysisPacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2023

J. Domingo-Ferrer

233

21

0

24 Feb 2023

Poisoning Web-Scale Training Datasets is Practical

Poisoning Web-Scale Training Datasets is PracticalIEEE Symposium on Security and Privacy (IEEE S&P), 2023

Nicholas Carlini

Matthew Jagielski

Christopher A. Choquette-Choo

Hyrum S. Anderson

Florian Tramèr

381

270

0

20 Feb 2023

Backdoor Learning for NLP: Recent Advances, Challenges, and Future
Research Directions

Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions

211

21

0

14 Feb 2023

SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via
Analyzing Scaled Prediction Consistency

SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction ConsistencyInternational Conference on Learning Representations (ICLR), 2023

Hanqing Guo

Lichao Sun

210

135

0

07 Feb 2023

BackdoorBox: A Python Toolbox for Backdoor Learning

BackdoorBox: A Python Toolbox for Backdoor Learning

226

50

0

01 Feb 2023

Page 1 of 2