paper-with-me

Papers

Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programming

2026-02-18 · Philip Sosnin, Jodie Knapp, Fraser Kennedy, Josh Collyer, Calvin Tsay arxiv

This work introduces a verification framework that provides both sound and complete guarantees for data poisoning attacks during neural network training. We formulate adversarial data manipulation, model training, and test-time evaluation in a single mixed-integer quadratic programming (MIQCP) problem. Finding the global optimum of the proposed formulation provably yields worst-case poisoning attacks, while simultaneously bounding the effectiveness of all possible attacks on the given training pipeline. Our framework encodes both the gradient-based training dynamics and model evaluation at test time, enabling the first exact certification of training-time robustness. Experimental evaluation on small models confirms that our approach delivers a complete characterization of robustness against data poisoning.

📄 PDF Abstract BibTeX arXiv:2602.16944

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

2022-03-16 · ICLR 2022 4 · Fan Wu, Linyi Li, Chejian Xu, huan zhang 외

As reinforcement learning (RL) has achieved near human-level performance in a variety of tasks, its robustness has raised great attention. While a vast body of research has explored test-time (evasion) attacks in RL and …

Offline RLreinforcement-learningReinforcement Learning (RL)

Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks

2023-08-15 · Shijie Liu, Andrew C. Cullen, Paul Montague, Sarah M. Erfani 외

Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees…

Adversarial Robustness

BiCert: A Bilinear Mixed Integer Programming Formulation for Precise Certified Bounds Against Data Poisoning Attacks

2024-12-13 · Tobias Lorenz, Marta Kwiatkowska, Mario Fritz

Data poisoning attacks pose one of the biggest threats to modern AI systems, necessitating robust defenses. While extensive efforts have been made to develop empirical defenses, attackers continue to evolve, creating sop…

Data Poisoning

Learning and Certification under Instance-targeted Poisoning

2021-05-18 · Ji Gao, Amin Karbasi, Mohammad Mahmoody

In this paper, we study PAC learnability and certification of predictions under instance-targeted poisoning attacks, where the adversary who knows the test instance may change a fraction of the training set with the goal…

PAC learning

Exact Certification of (Graph) Neural Networks Against Label Poisoning

2024-11-30 · Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann, Debarghya Ghoshdastidar

Machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustness certificates is important to guarant…

Bilevel OptimizationNode Classification