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.
Scanning Trojaned Models Using Out-of-Distribution Samples
UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
Retrievals Can Be Detrimental: A Contrastive Backdoor Attack Paradigm on Retrieval-Augmented Diffusion Models
Cooperative Decentralized Backdoor Attacks on Vertical Federated Learning
Energy Backdoor Attack to Deep Neural Networks
A4O: All Trigger for One sample
BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
HoneypotNet: Backdoor Attacks Against Model Extraction
Stealthy Backdoor Attack to Real-world Models in Android Apps
CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
Injecting Bias into Text Classification Models using Backdoor Attacks
Double Landmines: Invisible Textual Backdoor Attacks based on Dual-Trigger
Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning
A Backdoor Attack Scheme with Invisible Triggers Based on Model Architecture Modification
BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
Stealthy and Robust Backdoor Attack against 3D Point Clouds through Additional Point Features
An Effective and Resilient Backdoor Attack Framework against Deep Neural Networks and Vision Transformers
Data Free Backdoor Attacks
Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer
Backdooring Outlier Detection Methods: A Novel Attack Approach
LaserGuider: A Laser Based Physical Backdoor Attack against Deep Neural Networks
PBP: Post-training Backdoor Purification for Malware Classifiers
Behavior Backdoor for Deep Learning Models
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm
Streamlined Federated Unlearning: Unite as One to Be Highly Efficient
BadScan: An Architectural Backdoor Attack on Visual State Space Models
BadSFL: Backdoor Attack against Scaffold Federated Learning
LoBAM: LoRA-Based Backdoor Attack on Model Merging
AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
Memory Backdoor Attacks on Neural Networks
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.