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.
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons
Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
WeDef: Weakly Supervised Backdoor Defense for Text Classification
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic
Model-Contrastive Learning for Backdoor Defense
Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation
Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Backdoor Defense via Decoupling the Training Process
Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire
Backdoor Defense with Machine Unlearning
Few-shot Backdoor Defense Using Shapley Estimation
FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
Backdoor Attack and Defense for Deep Regression
On Provable Backdoor Defense in Collaborative Learning
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
Rethinking the Trigger of Backdoor Attack
Towards Probabilistic Verification of Machine Unlearning
Clean-Label Backdoor Attacks on Video Recognition Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.