https://github.com/k1rezaei/run-off-election
공식 코드Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
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/kaiwenzha/contrastive-poisoning
공식 코드Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
https://github.com/kohpangwei/data-poisoning-journal-release
공식 코드Stronger Data Poisoning Attacks Break Data Sanitization Defenses
https://github.com/lafeat/ueraser
공식 코드Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks
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/lhfowl/adversarial_poisons
공식 코드https://github.com/liangzid/lora-ssecurity
공식 코드Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
https://github.com/liu00222/PORE-Provably-Robust-Recommender-Systems-against-Data-Poisoning-Attacks
공식 코드PORE: Provably Robust Recommender Systems against Data Poisoning Attacks
https://github.com/liudaizong/awesome-lvlm-attack
공식 코드A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
https://github.com/lpd-epfl/attack_equivalence
공식 코드An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
https://github.com/luka-group/dpoe
공식 코드From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
https://github.com/martinpawel/openunlearn
공식 코드https://github.com/meghabyte/verifiable-training
공식 코드Optimistic Verifiable Training by Controlling Hardware Nondeterminism
https://github.com/microsoft/codegenerationpoisoning
공식 코드https://github.com/minhhao97vn/hint
공식 코드HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks
https://github.com/mmazeika/glc
공식 코드Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
https://github.com/nanboy-ronan/backdoor-fedgan
공식 코드Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
https://github.com/narenmanoj/mnist-adv-training
공식 코드https://github.com/ndraeger/waba
공식 코드Backdoor Attacks for Remote Sensing Data with Wavelet Transform
https://github.com/neeharperi/DeepKNNDefense
공식 코드Deep k-NN Defense against Clean-label Data Poisoning Attacks
https://github.com/nhuang37/dimensionality_reduction
공식 코드Dimensionality reduction, regularization, and generalization in overparameterized regressions
https://github.com/nishadsinghi/cleanclip
공식 코드CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning
https://github.com/optml-group/bibaddiff
공식 코드From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
https://github.com/orionw/disinformation-defense
공식 코드Defending Against Disinformation Attacks in Open-Domain Question Answering
https://github.com/papamarkou/neurotron_experiments
공식 코드https://github.com/perubhardwaj/attributionattack
공식 코드Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods
https://github.com/perubhardwaj/inferenceattack
공식 코드Poisoning Knowledge Graph Embeddings via Relation Inference Patterns
https://github.com/pinlong-zhao/data-poisoning
공식 코드https://github.com/pkiourti/rl_backdoor
공식 코드TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
https://github.com/pnnl/projection_ntk
공식 코드Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
https://github.com/prolearner/nonsmooth_implicit_diff
공식 코드Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates
https://github.com/psandovalsegura/autoregressive-poisoning
공식 코드https://github.com/psosnin/AbstractGradientTraining
공식 코드Certified Robustness to Data Poisoning in Gradient-Based Training
https://github.com/qiuyuezhibo/xaieeg
공식 코드Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG Signals
https://github.com/rookiezxy/gbtl
공식 코드Learning to Poison Large Language Models for Downstream Manipulation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.