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.
FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
TARGET: Template-Transferable Backdoor Attack Against Prompt-based NLP Models via GPT4
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Universal Jailbreak Backdoors from Poisoned Human Feedback
Attacks on fairness in Federated Learning
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
Label Poisoning is All You Need
CBD: A Certified Backdoor Detector Based on Local Dominant Probability
PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
Invisible Threats: Backdoor Attack in OCR Systems
Prompt Backdoors in Visual Prompt Learning
Composite Backdoor Attacks Against Large Language Models
Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the Physical World
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning
VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic Classification
Robust Backdoor Attacks on Object Detection in Real World
Physical Invisible Backdoor Based on Camera Imaging
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems
Exploiting Machine Unlearning for Backdoor Attacks in Deep Learning System
EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events
Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack
FTA: Stealthy and Adaptive Backdoor Attack with Flexible Triggers on Federated Learning
MDTD: A Multi Domain Trojan Detector for Deep Neural Networks
Protect Federated Learning Against Backdoor Attacks via Data-Free Trigger Generation
PatchBackdoor: Backdoor Attack against Deep Neural Networks without Model Modification
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.