https://github.com/rorschachchen/pipd
공식 코드Progressive Poisoned Data Isolation for Training-time Backdoor Defense
Papers with Code 아카이브
Data Poisoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Data Poisoning is an adversarial attack that tries to manipulate the training dataset in order to control the prediction behavior of a trained model such that the model will label malicious examples into a desired classes (e.g., labeling spam e-mails as safe).
Source: Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/rssalessio/data-poisoning-linear-systems
공식 코드Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
https://github.com/rssalessio/poisoning-data-driven-controllers
공식 코드Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
https://github.com/ruoxi-jia-group/meta-sift
공식 코드How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
https://github.com/sandamal/lid-regression
공식 코드https://github.com/sandamal/lid-svm
공식 코드Defending Distributed Classifiers Against Data Poisoning Attacks
https://github.com/saper0/qpcert
공식 코드Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
https://github.com/sclbd/backdoorbench
공식 코드Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
https://github.com/sesarlab/ensemble-random-forest-robustness-against-poisoning
공식 코드On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach
https://github.com/sf-zhai/badt2i
공식 코드Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning
https://github.com/shawkui/Proactive_Defensive_Backdoor
공식 코드Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
https://github.com/soroushzargar/cas
공식 코드https://github.com/stapaw/stp
공식 코드Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
https://github.com/stavc/unleashingworms-extractingdata
공식 코드https://github.com/t-lorenz/fullcert
공식 코드FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
https://github.com/terrytong-git/poisonshare
공식 코드Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
https://github.com/thanhtrunghuynh93/fastfedul
공식 코드Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
https://github.com/tianyu139/friendly-noise
공식 코드Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
https://github.com/tingchenfu/poisonbench
공식 코드PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
https://github.com/trustmlrg/transpoison
공식 코드https://github.com/tudelft-cda-lab/privatree
공식 코드Differentially-Private Decision Trees and Provable Robustness to Data Poisoning
https://github.com/tzvilederer/silent-killer
공식 코드Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
https://github.com/ucdvision/patchsearch
공식 코드Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning
https://github.com/umd-huang-lab/vlm-poisoning
공식 코드Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
https://github.com/unispac/subnet-replacement-attack
공식 코드Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks
https://github.com/v587su/coprotector
공식 코드CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoning
https://github.com/victoriagraf/nested_poe
공식 코드Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
https://github.com/vio1etus/flpoison
공식 코드SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
https://github.com/wangwenxiao/FiniteAggregation
공식 코드Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation
https://github.com/warisgill/FedDefender
공식 코드https://github.com/waterpine/nbc-missing
공식 코드Naive Bayes Classifiers over Missing Data: Decision and Poisoning
https://github.com/watml/plim
공식 코드Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attacks
https://github.com/watml/tgda-attack
공식 코드https://github.com/wisdeth14/molerecruitment
공식 코드Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Sampling
https://github.com/wronnyhuang/metapoison
공식 코드MetaPoison: Practical General-purpose Clean-label Data Poisoning
https://github.com/xingjunm/awesome-large-model-safety
공식 코드Safety at Scale: A Comprehensive Survey of Large Model Safety
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.