Early analog computers in Sweden-with examples from Chalmers University of technology and the Swedish aerospace industry

Abstract

Membership inference attacks (MIAs) aim to determine whether specific data were used to train a model. While extensively studied on classification models, their impact on time series forecasting remains largely unexplored. We address this gap by introducing two new attacks: (i) an adaptation of multivariate LiRA, a state-of-the-art MIA originally developed for classification models, to the time-series forecasting setting, and (ii) a novel end-to-end learning approach called Deep Time Series (DTS) attack. We benchmark these methods against adapted versions of other leading attacks from the classification setting.We evaluate all attacks in realistic settings on the TUH-EEG and ELD datasets, targeting two strong forecasting architectures, LSTM and the state-of-the-art N-HiTS, under both record-and user-level threat models. Our results show that forecasting models are vulnerable, with user-level attacks often achieving perfect detection. The proposed methods achieve the strongest performance in several settings, establishing new baselines for privacy risk assessment in time series forecasting. Furthermore, vulnerability increases with longer prediction horizons and smaller training populations, echoing trends observed in large language models.

Vessel detection and classification from spaceborne optical images: A literature survey

“…A relatively large fraction of the authors (35%) used Google Earth images as the direct input data source in their research on vessel detection – either as exported data or simply as a print screen –, or as a source for collecting the greater amount of test data for machine learning methods (An et al, 2013, p. 201; Deng et al, 2013, Dong et al, 2013, Gan et al, 2015, Guo et al, 2015, Han et al, 2014, Hong et al, 2007, Huang et al, 2016, Johansson, 2011, Ju, 2015, Ma et al, 2010, p. 201; Shi et al, 2014, Xu et al, 2017, Xu et al, 2011, p. 201; Xu and Liu, 2016, Xu et al, 2014, Yang et al, 2017, Yang et al, 2014, You and Li, 2011, Zhang et al, 2016, Zou and Shi, 2016). One author has used data from Microsoft Virtual Earth (Yin et al, 2016).…”

“…Land that is incorrectly classified is removed according to the difference of variance in the statistical model. From all of the accessible publications, only very few (Johansson, 2011, Topputo et al, 2016) manually removed areas of land from the image.…”

“…Other classifiers that were also used for vessel classification were: Bayesian classifier (Antelo et al, 2009), random forest (Johansson, 2011), Fisher classification (Zhang et al, 2012), adaptive boosting algorithm (Shi et al, 2014) and dynamic probability generative model (Guo et al, 2014). …”

Vessel detection and classification from spaceborne optical images: A literature survey

“…A relatively large fraction of the authors (35%) used Google Earth images as the direct input data source in their research on vessel detection – either as exported data or simply as a print screen –, or as a source for collecting the greater amount of test data for machine learning methods (An et al, 2013, p. 201; Deng et al, 2013, Dong et al, 2013, Gan et al, 2015, Guo et al, 2015, Han et al, 2014, Hong et al, 2007, Huang et al, 2016, Johansson, 2011, Ju, 2015, Ma et al, 2010, p. 201; Shi et al, 2014, Xu et al, 2017, Xu et al, 2011, p. 201; Xu and Liu, 2016, Xu et al, 2014, Yang et al, 2017, Yang et al, 2014, You and Li, 2011, Zhang et al, 2016, Zou and Shi, 2016). One author has used data from Microsoft Virtual Earth (Yin et al, 2016).…”

“…Land that is incorrectly classified is removed according to the difference of variance in the statistical model. From all of the accessible publications, only very few (Johansson, 2011, Topputo et al, 2016) manually removed areas of land from the image.…”

“…Other classifiers that were also used for vessel classification were: Bayesian classifier (Antelo et al, 2009), random forest (Johansson, 2011), Fisher classification (Zhang et al, 2012), adaptive boosting algorithm (Shi et al, 2014) and dynamic probability generative model (Guo et al, 2014). …”

In Situ Studies of Sulfate Nest Formation on Iron

“…Due to their higher OHconcentration, cathodic areas possess higher SO 2 deposition rates in the aqueous adlayer. 12,48 The higher SO 2 deposition rates in cathodic areas, combined with high concentrations of dissolved Fe 2ϩ and Fe 3ϩ ions migrating from anodic to cathodic areas, favor SO 2 oxidation to sulfate ions, as discussed in a previous section. This enhances iron dissolution and thereby creates new anodic sites and moves the cathodic areas.…”

Interferometry Method as a Way to Find Nonlinear Optical Responses of Nanoparticles

“…We have synthesized anatase TiO 2 nanoparticles by a sol-gel and hydrothermal process via modified barbe's method [12]. All materials were purchased from Merck and water was purified by distillation and filtration (Milli-Q).…”

Vessel detection and classification from spaceborne optical images: A literature survey

“…A relatively large fraction of the authors (35%) used Google Earth images as the direct input data source in their research on vessel detection – either as exported data or simply as a print screen –, or as a source for collecting the greater amount of test data for machine learning methods (An et al, 2013, p. 201; Deng et al, 2013, Dong et al, 2013, Gan et al, 2015, Guo et al, 2015, Han et al, 2014, Hong et al, 2007, Huang et al, 2016, Johansson, 2011, Ju, 2015, Ma et al, 2010, p. 201; Shi et al, 2014, Xu et al, 2017, Xu et al, 2011, p. 201; Xu and Liu, 2016, Xu et al, 2014, Yang et al, 2017, Yang et al, 2014, You and Li, 2011, Zhang et al, 2016, Zou and Shi, 2016). One author has used data from Microsoft Virtual Earth (Yin et al, 2016).…”

“…Land that is incorrectly classified is removed according to the difference of variance in the statistical model. From all of the accessible publications, only very few (Johansson, 2011, Topputo et al, 2016) manually removed areas of land from the image.…”

“…Other classifiers that were also used for vessel classification were: Bayesian classifier (Antelo et al, 2009), random forest (Johansson, 2011), Fisher classification (Zhang et al, 2012), adaptive boosting algorithm (Shi et al, 2014) and dynamic probability generative model (Guo et al, 2014). …”

In Situ Studies of Sulfate Nest Formation on Iron

“…Due to their higher OHconcentration, cathodic areas possess higher SO 2 deposition rates in the aqueous adlayer. 12,48 The higher SO 2 deposition rates in cathodic areas, combined with high concentrations of dissolved Fe 2ϩ and Fe 3ϩ ions migrating from anodic to cathodic areas, favor SO 2 oxidation to sulfate ions, as discussed in a previous section. This enhances iron dissolution and thereby creates new anodic sites and moves the cathodic areas.…”

Interferometry Method as a Way to Find Nonlinear Optical Responses of Nanoparticles

“…We have synthesized anatase TiO 2 nanoparticles by a sol-gel and hydrothermal process via modified barbe's method [12]. All materials were purchased from Merck and water was purified by distillation and filtration (Milli-Q).…”

Vessel detection and classification from spaceborne optical images: A literature survey

“…A relatively large fraction of the authors (35%) used Google Earth images as the direct input data source in their research on vessel detection – either as exported data or simply as a print screen –, or as a source for collecting the greater amount of test data for machine learning methods (An et al, 2013, p. 201; Deng et al, 2013, Dong et al, 2013, Gan et al, 2015, Guo et al, 2015, Han et al, 2014, Hong et al, 2007, Huang et al, 2016, Johansson, 2011, Ju, 2015, Ma et al, 2010, p. 201; Shi et al, 2014, Xu et al, 2017, Xu et al, 2011, p. 201; Xu and Liu, 2016, Xu et al, 2014, Yang et al, 2017, Yang et al, 2014, You and Li, 2011, Zhang et al, 2016, Zou and Shi, 2016). One author has used data from Microsoft Virtual Earth (Yin et al, 2016).…”

“…Land that is incorrectly classified is removed according to the difference of variance in the statistical model. From all of the accessible publications, only very few (Johansson, 2011, Topputo et al, 2016) manually removed areas of land from the image.…”

“…Other classifiers that were also used for vessel classification were: Bayesian classifier (Antelo et al, 2009), random forest (Johansson, 2011), Fisher classification (Zhang et al, 2012), adaptive boosting algorithm (Shi et al, 2014) and dynamic probability generative model (Guo et al, 2014). …”

In Situ Studies of Sulfate Nest Formation on Iron

“…Due to their higher OHconcentration, cathodic areas possess higher SO 2 deposition rates in the aqueous adlayer. 12,48 The higher SO 2 deposition rates in cathodic areas, combined with high concentrations of dissolved Fe 2ϩ and Fe 3ϩ ions migrating from anodic to cathodic areas, favor SO 2 oxidation to sulfate ions, as discussed in a previous section. This enhances iron dissolution and thereby creates new anodic sites and moves the cathodic areas.…”

Interferometry Method as a Way to Find Nonlinear Optical Responses of Nanoparticles

“…We have synthesized anatase TiO 2 nanoparticles by a sol-gel and hydrothermal process via modified barbe's method [12]. All materials were purchased from Merck and water was purified by distillation and filtration (Milli-Q).…”