Efficient poisoning attack converges to any target classifier with provable convergence.
problem Inducing a corrupted model that misbehaves in favor of an adversary.
method Online convex optimization to find poisoning points incrementally.
result Provably converges to any attainable target classifier.
Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.
problem Understanding and quantifying data poisoning in linear models.
method Analysis of ridge least squares with an unpenalized intercept, using resolvent techniques and random matrix theory.
result Closed-form limits for the poisoned score, revealing scaling laws and weight alignment with the poisoning direction.
MetaPoison poisons neural networks by learning to craft imperceptible changes to training data.
problem Data poisoning attacks on neural networks.
method MetaPoison uses meta-learning to approximate bilevel optimization for crafting poisons.
result MetaPoison outperforms previous methods and works in various scenarios.
Unified benchmarks assess data poisoning and backdoor attacks.
problem Unclear danger and effectiveness of data poisoning methods.
method Developed standardized benchmarks for data poisoning and backdoor attacks.
result Existing methods may not generalize to realistic settings.
Temporal threat model defends against data poisoning with timestamps.
problem Adversaries can poison more samples than expected, rendering existing defenses ineffective.
method Leverage timestamps to define earliness and duration metrics for temporal robustness.
result Temporal aggregation provides provable temporal robustness against data poisoning.
This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.
problem The effectiveness of targeted data poisoning attacks is often overestimated due to average evaluation methods.
method The paper introduces metrics to identify the hardest and easiest to poison samples based on clean model information.
result The proposed metrics reliably stratify samples by poisoning vulnerability, enabling rigorous worst-case evaluation and proactive defense.
Poisoning attack is identified as a severe security threat to machine learning algorithms. In many applications, for example, deep neural network (DNN) models collect public data as the inputs to perform re-training, where the input data can be poisoned. Although poisoning attack against support vector machines (SVM) h…
New method defends RL agents from poisoning attacks without MDP knowledge.
problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.
Paper shows large models are vulnerable to poisoning attacks.
problem Vulnerability of large machine learning models to poisoning attacks.
method Analyzed isotropic random feature vectors and geometric median as robust gradient aggregator rule.
result Linear and logistic regressions with D≥169H2/P2 parameters are vulnerable to arbitrary manipulation by poisoners. Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks that succeed without access to the victim network's outputs, architecture, or (i…
Aggregation defenses improve deep learning models' robustness against data poisoning attacks.
problem Data poisoning attacks manipulate deep learning models with malicious training samples.
method Deep Partition Aggregation, efficiency improvements, data-to-complexity ratio, poisoning overfitting phenomenon.
result Aggregation defenses boost poisoning robustness through the poisoning overfitting phenomenon.
Bullseye Polytope improves clean-label poisoning attacks in transfer learning.
problem Poisoning neural networks with correctly labeled data.
method Creates poison images with centers close to target images in feature space.
result Improves attack success rate by 26.75% in end-to-end transfer learning.
Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the …
New defence against data-poisoning attacks in neural networks.
problem Data-poisoning attacks can evade existing defences and increase model efficacy.
method Proved geometric mechanism and identified near clone regime in input space.
result Regularisation and data augmentation reduce data fitting capacity and prevent poisoning.
Poisoning attacks can undermine fairness in machine learning models.
problem Poisoning attacks can introduce classification disparities among different groups in data.
method Developed a gradient-based poisoning attack framework to target algorithmic fairness.
result Demonstrated the effectiveness of poisoning attacks in both white-box and black-box scenarios.
Paper proves mathematically that poisoning datasets can be detected.
problem Detecting data poisoning attacks in datasets.
method Mathematical definition and Conformal Separability Test.
result Dataset poisoning can be effectively detected.
Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural networks (DNNs) by inserting a backdoor pattern in the training images. The resulting…
Paper introduces class-oriented poisoning attacks to improve adversarial availability attacks.
problem Improving adversarial availability attacks on neural networks.
method Gradient-based framework for crafting poisoned images at the class level.
result Demonstrated effectiveness of class-oriented poisoning attacks on various models and datasets.
Research evaluates data poisoning attacks on regression learning and introduces a new defense strategy.
problem Data poisoning attacks on regression learning threaten model integrity in critical systems.
method Realistic scenarios, novel black-box attack, and evaluation on 26 datasets.
result Mean squared error (MSE) increases to 150% with only 2% poisoned samples.
This paper proposes a framework for certifying neural network defenses against data poisoning attacks.
problem Vulnerability of neural networks to data poisoning attacks.
method Random selection based defenses that average predictions on sub-datasets sampled from the training set.
result The certified radius of bagging derived by the framework is tighter than previous work.
Data poisoning attacks can severely degrade FL models, especially targeting specific classes.
problem Data poisoning attacks against federated learning systems.
method Demonstrated targeted attacks on FL systems, analyzed attack longevity, and proposed a defense strategy.
result Data poisoning attacks can cause substantial drops in classification accuracy and recall with a small percentage of malicious participants.
Paper explores how poisoning data can increase privacy risks in machine learning models.
problem Increasing privacy risks of benign training samples through data poisoning attacks.
method Proposes generic and optimization-based attacks to amplify membership exposure.
result Demonstrates substantial increase in membership inference precision with minimal model performance degradation.
Improved defense against data poisoning attacks by aggregating smaller subsets.
problem Mitigating the impact of poisoned data on model robustness.
method Finite Aggregation method that combines duplicates of smaller disjoint subsets for training.
result Consistent improvement in certified robustness bounds, up to 4.77% on GTSRB.
Paper shows data poisoning and Byzantine attacks are equivalent, impacting federated learning security.
problem Resilience of federated learning systems to adversarial attacks.
method Proved equivalence between data poisoning and Byzantine gradient attacks.
result Equivalence between data poisoning and Byzantine attacks in federated learning.
Deep Partition Aggregation defends against poisoning attacks with provable certificates.
problem Adversarial poisoning attacks corrupt classifier test-time behavior.
method Deep Partition Aggregation (DPA) is an ensemble method using hash partitions and base models trained on these partitions.
result DPA can certify >= 50% of test images against over 500 poison image insertions on MNIST, and nine insertions on CIFAR-10.
Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of prior work has developed attacks and defenses, there is not much general understan…
FLANDERS detects and blocks extreme model poisoning in federated learning.
problem Resilience against large-scale model poisoning attacks in federated learning.
method FLANDERS treats client updates as matrix-valued time series and identifies outliers using autoregressive forecasting.
result FLANDERS significantly improves robustness in federated learning across various attacks.
The Lethal Dose Conjecture limits how much poisoned data can be tolerated.
problem Limiting the impact of poisoned data in machine learning models.
method Theoretical analysis and provable defenses (DPA, FA) based on majority voting.
result DPA and FA are asymptotically optimal defenses against data poisoning.
Regularization can improve machine learning models' robustness against poisoning attacks.
problem Poisoning attacks degrade machine learning models' performance by manipulating a fraction of the training data.
method Proposes a novel optimal attack formulation considering the effect of hyperparameters on regularization, leading to better evaluation of robustness.
result Demonstrates that L2 regularization can help mitigate the impact of poisoning attacks. Defense against backdoor attacks by clustering incompatible data subsets.
problem Backdoor poisoning attacks on deep neural networks.
method Incompatibility clustering of data subsets during training.
result Successfully reduces attack success rate to below 1%.
Trustworthy AI is a critical issue in machine learning where, in addition to training a model that is accurate, one must consider both fair and robust training in the presence of data bias and poisoning. However, the existing model fairness techniques mistakenly view poisoned data as an additional bias to be fixed, res…
Paper proposes a game-theoretic approach to generate unlearnable examples.
problem Generating imperceptible perturbations to degrade deep learning models.
method Formulated as a Stackelberg game, proposing a novel attack method GUE.
result GUE effectively poisons models with minimal training data and generalizes well.
New research shows Byzantine failures hurt generalization more than data poisoning in robust distributed learning.
problem Generalization in robust distributed learning algorithms under Byzantine failures vs. data poisoning.
method Algorithmic stability analysis of robust distributed learning algorithms.
result Byzantine failures yield strictly worse generalization rates than data poisoning.
Machine learning (ML) over distributed multi-party data is required for a variety of domains. Existing approaches, such as federated learning, collect the outputs computed by a group of devices at a central aggregator and run iterative algorithms to train a globally shared model. Unfortunately, such approaches are susc…
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-le…
Subpopulation attacks poison data to misclassify naturally distributed points.
problem Improving accuracy of machine learning predictions through adversarial data modification.
method Introducing a novel subpopulation attack framework, using influence functions and gradient optimization.
result Subpopulation attacks are effective and stealthy, making them difficult to defend against.
Machine learning models trained on data from the outside world can be corrupted by data poisoning attacks that inject malicious points into the models' training sets. A common defense against these attacks is data sanitization: first filter out anomalous training points before training the model. In this paper, we deve…
New defense mechanism detects and mitigates poisoned regression data.
problem Vulnerability of regression models to targeted data poisoning attacks.
method Introduces N-LID, a measure of local intrinsic dimensionality to distinguish poisoned samples.
result N-LID based defense outperforms state-of-the-art methods in prediction accuracy and runtime.
Bayesian models can be tricked into believing false data.
problem Vulnerability of Bayesian inference to data poisoning attacks.
method Developed attacks to manipulate Bayesian posterior through deletion and replication of data.
result Demonstrated that Bayesian inference can be steered to target distributions.
Poisoning datasets can reveal private details of other users' training points.
problem Integrity and privacy of machine learning training data.
method Active inference attacks that poison a small fraction of the training dataset.
result Poisoning as little as 0.1% of the training dataset can significantly boost inference attacks.
We use distributionally-robust optimization for machine learning to mitigate the effect of data poisoning attacks. We provide performance guarantees for the trained model on the original data (not including the poison records) by training the model for the worst-case distribution on a neighbourhood around the empirical…
New study shows data-oblivious attacks can outperform data-aware ones.
problem Comparing effectiveness of data-oblivious and data-aware poisoning attacks.
method Theoretical study of feature selection with LASSO, focusing on separation between full-information and oblivious attackers.
result Data-oblivious attacks can achieve the same results as full-information attacks for feature selection with LASSO.
New method optimizes ML models under poisoned data, improving robustness.
problem Vulnerability of ML models to poisoned data attacks.
method Multiobjective bilevel optimization to consider hyperparameter learning and attack effects.
result Current approaches underestimate model robustness and regularization benefits.
Paper develops a robust federated recommendation system against poisoning attacks.
problem Low-cost poisoning attacks degrade federated recommendation systems' performance.
method Develops a robust learning strategy using gradients to filter out Byzantine clients.
result Empirically validated robust learning strategy on four datasets.
Dynamic defense against Byzantine poisoning in federated learning.
problem Byzantine poisoning attacks on federated learning models.
method Dynamic federated aggregation operator to filter out adversarial clients.
result Dynamic selection of clients improves global learning model performance.
Timber targets decision trees, outperforming existing attacks.
problem Poisoning decision trees to manipulate model predictions.
method Greedy attack strategy using sub-tree retraining for efficiency.
result Timber outperforms existing attacks in effectiveness and efficiency.
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an ind…
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous work, but the underlying reasons why an attack transfers or not are not yet well understood. In this paper…