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.
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
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
Adversarial Backdoor Defense in CLIP
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
Data-centric NLP Backdoor Defense from the Lens of Memorization
PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models
TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
Backdoor defense, learnability and obfuscation
Backdoor Defense through Self-Supervised and Generative Learning
Fisher Information guided Purification against Backdoor Attacks
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification
Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning
Protecting against simultaneous data poisoning attacks
Eliminating Backdoors in Neural Code Models for Secure Code Understanding
Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense
Defense Against Syntactic Textual Backdoor Attacks with Token Substitution
Robustness Inspired Graph Backdoor Defense
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective
Magnitude-based Neuron Pruning for Backdoor Defens
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
Interactive Simulations of Backdoors in Neural Networks
BadActs: A Universal Backdoor Defense in the Activation Space
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.