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.
BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
You Can Backdoor Personalized Federated Learning
Beating Backdoor Attack at Its Own Game
Adversarial Feature Map Pruning for Backdoor
Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification
Rethinking Backdoor Attacks
Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives
FedDefender: Backdoor Attack Defense in Federated Learning
Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion
Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving
Hidden Backdoor Attack against Deep Learning-Based Wireless Signal Modulation Classifiers
Bkd-FedGNN: A Benchmark for Classification Backdoor Attacks on Federated Graph Neural Network
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios
VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
Mitigating Backdoor Attack Via Prerequisite Transformation
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
Backdoor Attacks Against Incremental Learners: An Empirical Evaluation Study
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
UOR: Universal Backdoor Attacks on Pre-trained Language Models
Backdoor Attack with Sparse and Invisible Trigger
Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning
BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks
Defending against Insertion-based Textual Backdoor Attacks via Attribution
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
DABS: Data-Agnostic Backdoor attack at the Server in Federated Learning
FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger
INK: Inheritable Natural Backdoor Attack Against Model Distillation
BadVFL: Backdoor Attacks in Vertical Federated Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.