https://github.com/ict-convergence-security-lab-chosun/sdba
공식 코드SDBA: A Stealthy and Long-Lasting Durable Backdoor Attack in Federated Learning
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/ink-usc/bite
공식 코드BITE: Textual Backdoor Attacks with Iterative Trigger Injection
https://github.com/invisibletriggerdiffusion/invisible_triggers_for_diffusion
공식 코드https://github.com/jcroh0508/msdt
공식 코드https://github.com/jeongjin0/invisible-backdoor-object-detection
공식 코드https://github.com/jhcknzzm/federated-learning-backdoor
공식 코드https://github.com/jiahaowugit/bgc
공식 코드https://github.com/jiawangbai/TA-LBF
공식 코드Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
https://github.com/jiawangbai/versatile-weight-attack
공식 코드https://github.com/jiazhaoli/attdef
공식 코드Defending against Insertion-based Textual Backdoor Attacks via Attribution
https://github.com/jinghuichen/Focused-Flip-Federated-Backdoor-Attack
공식 코드On the Vulnerability of Backdoor Defenses for Federated Learning
https://github.com/jinxhy/tflexattack
공식 코드https://github.com/jj-vice/bagm
공식 코드BAGM: A Backdoor Attack for Manipulating Text-to-Image Generative Models
https://github.com/jjy1994/BadEncoder
공식 코드BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
https://github.com/john-niu-07/pud
공식 코드Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
https://github.com/jrohsc/backdororing_bias
공식 코드https://github.com/judydnguyen/pbp-backdoor-purification-official
공식 코드PBP: Post-training Backdoor Purification for Malware Classifiers
https://github.com/jwliang007/pff
공식 코드Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
https://github.com/jzhang538/badmerging
공식 코드https://github.com/kaidi-jin/backdoor_samples_detection
공식 코드Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?
https://github.com/kirinng/dwb
공식 코드Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
https://github.com/lancopku/Embedding-Poisoning
공식 코드https://github.com/lancopku/agent-backdoor-attacks
공식 코드Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
https://github.com/leileigan/clean_label_textual_backdoor_attack
공식 코드https://github.com/liuyugeng/baadd
공식 코드https://github.com/magic-ma-tech/dfb
공식 코드DFB: A Data-Free, Low-Budget, and High-Efficacy Clean-Label Backdoor Attack
https://github.com/maoubo/unidoor
공식 코드UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning
https://github.com/martin-ochoa/foobar
공식 코드FooBaR: Fault Fooling Backdoor Attack on Neural Network Training
https://github.com/maxproto/iba
공식 코드https://github.com/meet-cjli/ctrl
공식 코드An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
https://github.com/megum1/beagle
공식 코드BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
https://github.com/megum1/lotus
공식 코드LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
https://github.com/minliu01/non-adversarial_backdoor
공식 코드https://github.com/miraclehh/cba
공식 코드https://github.com/momalab/ReVeil
공식 코드ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
https://github.com/mxzheng/trojvit
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.