Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization
Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal attacks can be formulated as bilevel optimization problems and help to assess their robustness in worst-case scenarios. We show that current approaches, which typically assume that hyperparameters remain constant, lead to an overly pessimistic view of the algorithms' robustness and of the impact of regularization. We propose a novel optimal attack formulation that considers the effect of the attack on the hyperparameters and models the attack as a multiobjective bilevel optimization problem. This allows to formulate optimal attacks, learn hyperparameters and evaluate robustness under worst-case conditions. We apply this attack formulation to several ML classifiers using $L_2$ and $L_1$ regularization. Our evaluation on multiple datasets confirms the limitations of previous strategies and evidences the benefits of using $L_2$ and $L_1$ regularization to dampen the effect of poisoning attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Bilevel OptimizationData PoisoningSimilar Papers 제목 키워드 기반
Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks ha…
BIG-bench Machine LearningIncremental LearningTurning Generative Models Degenerate: The Power of Data Poisoning Attacks
The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable …
Data Poisoningparameter-efficient fine-tuningText GenerationText SummarizationRegularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal poisoning attacks, which can be form…
Bilevel OptimizationData PoisoningL2 RegularizationMultiobjective OptimizationRegularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters
Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that r…
Bilevel OptimizationregressionDetect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
Training-time data poisoning during fine-tuning poses a significant threat to large language models (LLMs) deployed for abstractive text summarization, where small task-specific datasets exert disproportionate influence …
Abstractive Text Summarization