Papers with Code 아카이브
backdoor defense
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks
InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
Robust Anti-Backdoor Instruction Tuning in LVLMs
Spectral Insights into Data-Oblivious Critical Layers in Large Language Models
Heterogeneous Graph Backdoor Attack
FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
Cert-SSB: Toward Certified Sample-Specific Backdoor Defense
TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
Backdoor Defense in Diffusion Models via Spatial Attention Unlearning
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks
Prototype Guided Backdoor Defense
Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition
PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT Environments
Towards Backdoor Stealthiness in Model Parameter Space
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models
Neutralizing Backdoors through Information Conflicts for Large Language Models
MADE: Graph Backdoor Defense with Masked Unlearning
CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attacks
Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
BeniFul: Backdoor Defense via Middle Feature Analysis for Deep Neural Networks
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.