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.
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
FIGhost: Fluorescent Ink-based Stealthy and Flexible Backdoor Attacks on Physical Traffic Sign Recognition
Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning
MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
Protocol-agnostic and Data-free Backdoor Attacks on Pre-trained Models in RF Fingerprinting
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
SFIBA: Spatial-based Full-target Invisible Backdoor Attacks
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
Robo-Troj: Attacking LLM-based Task Planners
BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
Strategic Planning of Stealthy Backdoor Attacks in Markov Decision Processes
Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
A Channel-Triggered Backdoor Attack on Wireless Semantic Image Reconstruction
Backdoor Detection through Replicated Execution of Outsourced Training
DeBackdoor: A Deductive Framework for Detecting Backdoor Attacks on Deep Models with Limited Data
Towards Invisible Backdoor Attack on Text-to-Image Diffusion Model
A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
C^2 ATTACK: Towards Representation Backdoor on CLIP via Concept Confusion
Stealthy Patch-Wise Backdoor Attack in 3D Point Cloud via Curvature Awareness
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution
A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models
Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
Multi-Target Federated Backdoor Attack Based on Feature Aggregation
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness
ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.