Kleyko, D., Osipov, E., Papakonstantinou, N., Vyatkin, V.: Hyperdimensional computing in industrial systems: the use-case of distributed fault isolation in a power plant. In: IEEE International Conference on Artificial Intelligence Circuits and Systems (2019) In: Artificial Intelligence Applications and Innovations (2020)Ĭhang, E., Rahimi, A., Benini, L., Wu, A.A.: Hyperdimensional computing-based multimodality emotion recognition with physiological signals. IEEE Design Test 34(6), 94–101 (2017)Ĭhang, C.-Y., Chuang, Y.-C., Wu, A.-Y.A.: Task-projected hyperdimensional computing for multi-task learning. Imani, M., Hwang, J., Rosing, T., Rahimi, A., Rabaey, J.M.: Low-power sparse hyperdimensional encoder for language recognition. Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. In: DAC (2018)īenatti, S., Montagna, F., Kartsch, V., Rahimi, A., Rossi, D., Benini, L.: Online learning and classification of EMG-based gestures on a parallel ultra-low power platform using hyperdimensional computing. Imani, M., Huang, C., Kong, D., Rosing, T.: Hierarchical hyperdimensional computing for energy efficient classification. Imani, M., Morris, J., Messerly, J., Shu, H., Deng, Y., Rosing, T.: BRIC: Locality-based encoding for energy-efficient brain-inspired hyperdimensional computing. Kanerva, P.: Hyperdimensional computing: an introduction to computing in distributed representation. Karunaratne, G., Le Gallo, M., Cherubini, G., Benini, L., Rahimi, A., Sebastian, A.: In-memory Hyperdimensional Computing, Nature Electronics, June 2020 Ge, L., Parhi, K.K.: Classification using hyperdimensional computing: a review. Our results show that adversarial images can successfully mislead the HDC classifier to produce wrong prediction labels with a high probability (i.e., 78% when the HDC classifier uses a fixed majority rule for decision). Then, we propose a modified genetic algorithm to generate adversarial samples within a reasonably small number of queries, and further apply critical gene crossover and perturbation adjustment to limit the amount of perturbation noise. Specifically, using handwritten digit classification as an example, we construct a HDC classifier and formulate a grey-box attack problem, where an attacker’s goal is to mislead the target HDC classifier to produce erroneous prediction labels while keeping the amount of added perturbation noise as little as possible. In this paper, we study for the first time adversarial attacks on HDC classifiers and highlight that HDC classifiers can be vulnerable to even minimally-perturbed adversarial samples. Nonetheless, state-of-the-art designs for HDC classifiers are mostly security-oblivious, raising concerns with their safety and immunity to adversarial inputs. Hyperdimensional computing (HDC) has been emerging as a brain-inspired in-memory computing architecture, exhibiting ultra energy efficiency, low latency and strong robustness against hardware-induced bit errors.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |