Papers with Code 아카이브
backdoor defense
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/BililiCode/ARGD
공식 코드Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation
https://github.com/KaiyuanZh/FLIP
공식 코드FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
https://github.com/SJTUHaiyangYu/BackdoorMBTI
공식 코드BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
https://github.com/ShihaoZhaoZSH/Video-Backdoor-Attack
공식 코드https://github.com/aisafety-hkust/stable_backdoor_purification
공식 코드Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
https://github.com/bboylyg/expose-before-you-defend
공식 코드Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
https://github.com/bboylyg/rnp
공식 코드https://github.com/besticsp/fl-plas
공식 코드https://github.com/binyxu/CGD
공식 코드CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
https://github.com/blingcho/vflip-esorics24
공식 코드VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification
https://github.com/clearloveclearlove/BadActs
공식 코드BadActs: A Universal Backdoor Defense in the Activation Space
https://github.com/damianliumin/non-adversarial_backdoor
공식 코드https://github.com/graph-axis/gcleaner
공식 코드"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
https://github.com/hazardfy/fiba
공식 코드FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
https://github.com/illidanlab/abd
공식 코드Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
https://github.com/inspire-group/unlearning-verification
공식 코드https://github.com/jcroh0508/msdt
공식 코드https://github.com/jhy549/ocgec
공식 코드OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection
https://github.com/john-niu-07/pud
공식 코드Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
https://github.com/kuofenggao/asd
공식 코드https://github.com/lancopku/agent-backdoor-attacks
공식 코드Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
https://github.com/lancopku/dan
공식 코드Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
https://github.com/livxue/poisoncam
공식 코드Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking
https://github.com/luka-group/dpoe
공식 코드From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
https://github.com/magic-ma-tech/dfb
공식 코드DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack
https://github.com/minliu01/non-adversarial_backdoor
공식 코드https://github.com/naymyatmin/crow
공식 코드CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
https://github.com/nazmul-karim170/FIP-Fisher-Backdoor-Removal
공식 코드Fisher Information guided Purification against Backdoor Attacks
https://github.com/nazmul-karim170/natural-gradient-finetuning-trojan-defense
공식 코드Efficient Backdoor Removal Through Natural Gradient Fine-tuning
https://github.com/ncepuqiaoting/cert-ssb
공식 코드https://github.com/ndraeger/waba
공식 코드Backdoor Attacks for Remote Sensing Data with Wavelet Transform
https://github.com/optml-group/backdoormspc
공식 코드Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
https://github.com/optml-group/bibaddiff
공식 코드From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
https://github.com/paoche11/gungnir
공식 코드Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
https://github.com/pku-ml/terd
공식 코드TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.