Papers with Code 아카이브

Data Poisoning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/9yte/VenoMave

공식 코드

VenoMave: Targeted Poisoning Against Speech Recognition

https://github.com/AI-secure/Meta-Nerual-Trojan-Detection

공식 코드

Detecting AI Trojans Using Meta Neural Analysis

https://github.com/Cinofix/beta_poisoning

공식 코드

The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?

https://github.com/Fraunhofer-AISEC/regression-data-poisoning

공식 코드

Data Poisoning Attacks on Regression Learning and Corresponding Defenses

https://github.com/Fraunhofer-AISEC/regression_data_poisoning

공식 코드

Data Poisoning Attacks on Regression Learning and Corresponding Defenses

https://github.com/JonasGeiping/data-poisoning

공식 코드

Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff

https://github.com/JonasGeiping/poisoning-gradient-matching

공식 코드

Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching

https://github.com/JunW15/Monolingual-Attack

공식 코드

Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning

https://github.com/KuofengGao/CIBA

공식 코드

Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning

https://github.com/LCWN-Lab/Odyssey

공식 코드

Odyssey: Creation, Analysis and Detection of Trojan Models

https://github.com/MI2DataLab/fooling-partial-dependence

공식 코드

Fooling Partial Dependence via Data Poisoning

https://github.com/Ninarehm/attack

공식 코드

Exacerbating Algorithmic Bias through Fairness Attacks

https://github.com/PengfeiHePower/awesome-LLM-data-poisoning

공식 코드

Multi-Faceted Studies on Data Poisoning can Advance LLM Development

https://github.com/SJTUHaiyangYu/BackdoorMBTI

공식 코드

BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation

https://github.com/Sanghyun-Hong/Gradient-Shaping

공식 코드

On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping

https://github.com/SunayBhat1/PureGen_PoisonDefense

공식 코드

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics

https://github.com/THUYimingLi/backdoor-learning-resources

공식 코드

Backdoor Learning: A Survey

https://github.com/VADERASU/visual-analytics-adversarial-attacks

공식 코드

Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics

https://github.com/WuYunfan/GradientPassingAttack

공식 코드

Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems

https://github.com/YifanSun99/2d-oob

공식 코드

2D-OOB: Attributing Data Contribution Through Joint Valuation Framework

https://github.com/aks2203/poisoning-benchmark

공식 코드

Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks

https://github.com/akshaymehra24/LimitsOfUDA

공식 코드

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

https://github.com/akshaymehra24/poisoning_certified_defenses

공식 코드

How Robust are Randomized Smoothing based Defenses to Data Poisoning?

https://github.com/alignmentresearch/scaling-poisoning

공식 코드

Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws

https://github.com/alphaprime/Poisonging_Attack_Pairwise_Comparison

공식 코드

Poisoning Attack against Estimating from Pairwise Comparisons

https://github.com/amberyzheng/imma

공식 코드

IMMA: Immunizing text-to-image Models against Malicious Adaptation

https://github.com/aminesi/federated

공식 코드

Towards Understanding Quality Challenges of the Federated Learning for Neural Networks: A First Look from the Lens of Robustness

https://github.com/andreartelt/datapoisoningcounterfactuals

공식 코드

The Effect of Data Poisoning on Counterfactual Explanations

https://github.com/andyisokay/delta-influence

공식 코드

Delta-Influence: Unlearning Poisons via Influence Functions

https://github.com/anonymous10240/framework

공식 코드

Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models

https://github.com/ari-dasci/s-ddaba

공식 코드

Dynamic Defense Against Byzantine Poisoning Attacks in Federated Learning

https://github.com/aseriesof-tubes/RSK

공식 코드

Learning from Convolution-based Unlearnable Datasets

https://github.com/ashafahi/inceptionv3-transferLearn-poison

공식 코드

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

https://github.com/atenanaz/poison-rag

공식 코드

Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems

https://github.com/avinandan22/certified-robustness

공식 코드

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning

https://github.com/azshue/autopoison

공식 코드

On the Exploitability of Instruction Tuning

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.