Papers with Code 아카이브
Backdoor Attack
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee
Towards Imperceptible Backdoor Attack in Self-supervised Learning
TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models
EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection
An Invisible Backdoor Attack Based On Semantic Feature
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
Towards Robust Physical-world Backdoor Attacks on Lane Detection
Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
Let's Focus: Focused Backdoor Attack against Federated Transfer Learning
Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning
Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning
CloudFort: Enhancing Robustness of 3D Point Cloud Classification Against Backdoor Attacks via Spatial Partitioning and Ensemble Prediction
A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning
Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
SpamDam: Towards Privacy-Preserving and Adversary-Resistant SMS Spam Detection
How to Craft Backdoors with Unlabeled Data Alone?
Backdoor Attack on Multilingual Machine Translation
Exploring Backdoor Vulnerabilities of Chat Models
Manipulating and Mitigating Generative Model Biases without Retraining
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
Towards Adversarial Robustness And Backdoor Mitigation in SSL
BadEdit: Backdooring large language models by model editing
Mask-based Invisible Backdoor Attacks on Object Detection
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
Invisible Backdoor Attack Through Singular Value Decomposition
Backdoor Attack with Mode Mixture Latent Modification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.