@inproceedings{22294,
  abstract     = {Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an ML model to forget part of the data it was trained on. In this paper, we introduce a novel unlearning approach based on Forgetting Neural Networks (FNNs), a neuroscience-inspired architecture that explicitly encodes forgetting through multiplicative decay factors. While FNNs had previously been studied as a theoretical construct, we provide the first concrete implementation and demonstrate their effectiveness for targeted unlearning. We propose several variants with per-neuron forgetting factors, including rank-based assignments guided by activation levels, and evaluate them on MNIST and Fashion-MNIST benchmarks. Our method systematically removes information associated with forget sets while preserving performance on retained data. Membership inference attacks confirm the effectiveness of FNN-based unlearning in erasing information about the training data from the neural network. These results establish FNNs as a promising foundation for efficient and interpretable unlearning. },
  author       = {Hatua, Amartya and Nguyen, Trung and Cano Cordoba, Filip and Sung, Andrew},
  booktitle    = {Proceedings of the 18th International Conference on Agents and Artificial Intelligence},
  isbn         = {9789897587962},
  issn         = {2184-433X},
  keywords     = {Machine Unlearning, Neuroscience-Inspired Machine Learning, Membership Inference Attacks},
  location     = {Marbella, Spain},
  pages        = {1536--1546},
  publisher    = {SciTePress},
  title        = {{Machine unlearning using forgetting neural networks}},
  doi          = {10.5220/0014326500004052},
  volume       = {2},
  year         = {2026},
}

@inproceedings{22104,
  abstract     = { Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an ML model to forget part of the data it was trained on. In this paper, we introduce a novel unlearning approach based on Forgetting Neural Networks (FNNs), a neuroscience-inspired architecture that explicitly encodes forgetting through multiplicative decay factors. While FNNs had previously been studied as a theoretical construct, we provide the first concrete implementation and demonstrate their effectiveness for targeted unlearning. We propose several variants with per-neuron forgetting factors, including rank-based assignments guided by activation levels, and evaluate them on MNIST and Fashion-MNIST benchmarks. Our method systematically removes information associated with forget sets while preserving performance on retained data. Membership inference attacks confirm the effectiveness of FNN-based unlearning in erasing information about the training data from the neural network. These results establish FNNs as a promising foundation for efficient and interpretable unlearning.},
  author       = {Hatua, Amartya and Nguyen, Trung T. and Cano Cordoba, Filip and Sung, Andrew H.},
  booktitle    = {Proceedings of the 18th International Conference on Agents and Artificial Intelligence},
  isbn         = {9789897587962},
  issn         = {2184-433X},
  keywords     = {Machine Unlearning, Neuroscience-Inspired Machine Learning, Membership Inference Attacks},
  location     = {Marbella, Spain},
  pages        = {1536--1546},
  publisher    = {Science and Technology Publications},
  title        = {{Machine unlearning using forgetting neural networks}},
  doi          = {10.5220/0014326500004052},
  volume       = {2},
  year         = {2026},
}

@inproceedings{9200,
  abstract     = {Formal design of embedded and cyber-physical systems relies on mathematical modeling. In this paper, we consider the model class of hybrid automata whose dynamics are defined by affine differential equations. Given a set of time-series data, we present an algorithmic approach to synthesize a hybrid automaton exhibiting behavior that is close to the data, up to a specified precision, and changes in synchrony with the data. A fundamental problem in our synthesis algorithm is to check membership of a time series in a hybrid automaton. Our solution integrates reachability and optimization techniques for affine dynamical systems to obtain both a sufficient and a necessary condition for membership, combined in a refinement framework. The algorithm processes one time series at a time and hence can be interrupted, provide an intermediate result, and be resumed. We report experimental results demonstrating the applicability of our synthesis approach.},
  author       = {Garcia Soto, Miriam and Henzinger, Thomas A and Schilling, Christian},
  booktitle    = {HSCC '21: Proceedings of the 24th International Conference on Hybrid Systems: Computation and Control},
  isbn         = {9781450383394},
  keywords     = {hybrid automaton, membership, system identification},
  location     = {Nashville, TN, United States},
  pages        = {2102.12734},
  publisher    = {Association for Computing Machinery},
  title        = {{Synthesis of hybrid automata with affine dynamics from time-series data}},
  doi          = {10.1145/3447928.3456704},
  year         = {2021},
}

@inproceedings{6493,
  abstract     = {We present two algorithmic approaches for synthesizing linear hybrid automata from experimental data. Unlike previous approaches, our algorithms work without a template and generate an automaton with nondeterministic guards and invariants, and with an arbitrary number and topology of modes. They thus construct a succinct model from the data and provide formal guarantees. In particular, (1) the generated automaton can reproduce the data up to a specified tolerance and (2) the automaton is tight, given the first guarantee. Our first approach encodes the synthesis problem as a logical formula in the theory of linear arithmetic, which can then be solved by an SMT solver. This approach minimizes the number of modes in the resulting model but is only feasible for limited data sets. To address scalability, we propose a second approach that does not enforce to find a minimal model. The algorithm constructs an initial automaton and then iteratively extends the automaton based on processing new data. Therefore the algorithm is well-suited for online and synthesis-in-the-loop applications. The core of the algorithm is a membership query that checks whether, within the specified tolerance, a given data set can result from the execution of a given automaton. We solve this membership problem for linear hybrid automata by repeated reachability computations. We demonstrate the effectiveness of the algorithm on synthetic data sets and on cardiac-cell measurements.},
  author       = {Garcia Soto, Miriam and Henzinger, Thomas A and Schilling, Christian and Zeleznik, Luka},
  booktitle    = {31st International Conference on Computer-Aided Verification},
  isbn         = {9783030255398},
  issn         = {0302-9743},
  keywords     = {Synthesis, Linear hybrid automaton, Membership},
  location     = {New York City, NY, USA},
  pages        = {297--314},
  publisher    = {Springer},
  title        = {{Membership-based synthesis of linear hybrid automata}},
  doi          = {10.1007/978-3-030-25540-4_16},
  volume       = {11561},
  year         = {2019},
}

