Search for: All records

A metacognitive radar switches between two modes of cognition— one mode to achieve a high-quality estimate of targets, and the other mode to hide its utility function (plan). To achieve high-quality es- timates of targets, a cognitive radar performs a constrained utility maximization to adapt its sensing mode in response to a changing target environment. If an adversary can estimate the utility function of a cognitive radar, it can determine the radar’s sensing strategy and mitigate the radar performance via electronic countermeasures (ECM). This article discusses a metacognitive radar that switches between two modes of cognition: achieving satisfactory estimates of a target while hiding its strategy from an adversary that detects cognition. The radar does so by transmitting purposefully designed suboptimal responses to spoof the adversary’s Neyman–Pearson de- tector. We provide theoretical guarantees by ensuring that the Type-I error probability of the adversary’s detector exceeds a predefined level for a specified tolerance on the radar’s performance loss. We illustrate our cognition-masking scheme via numerical examples in- volving waveform adaptation and beam allocation. We show that small purposeful deviations from the optimal emission confuse the adversary by significant amounts, thereby masking the radar’s cognition. Our approach uses ideas from revealed preference in microeconomics and adversarial inverse reinforcement learning. Our proposed algorithms provide a principled approach for system-level electronic counter- countermeasures to hide the radar’s strategy from an adversary. We also provide performance bounds for our cognition-masking scheme when the adversary has misspecified measurements of the radar’s response. 

Inverse reinforcement learning (IRL) deals with estimating an agent’s utility function from its actions. In this paper, we consider how an agent can hide its strategy and mitigate an adversarial IRL attack; we call this inverse IRL (I-IRL). How should the decision maker choose its response to ensure a poor reconstruction of its strategy by an adversary performing IRL to estimate the agent’s strategy? This paper comprises four results: First, we present an adversarial IRL algorithm that estimates the agent’s strategy while controlling the agent’s utility function. Then, we propose an I-IRL result that mitigates the IRL algorithm used by the adversary. Our I-IRL results are based on revealed preference theory in microeconomics. The key idea is for the agent to deliberately choose sub-optimal responses so that its true strategy is sufficiently masked. Third, we give a sample complexity result for our main I-IRL result when the agent has noisy estimates of the adversary-specified utility function. Finally, we illustrate our I-IRL scheme in a radar problem where a meta-cognitive radar is trying to mitigate an adversarial target. 

Abstract There are few observed high-mass X-ray binaries (HMXBs) that harbor massive black holes (BHs), and none are likely to result in a binary black hole (BBH) that merges within a Hubble time; however, we know that massive merging BBHs exist from gravitational-wave (GW) observations. We investigate the role that X-ray and GW observational selection effects play in determining the properties of their respective detected binary populations. We find that, as a result of selection effects, detectable HMXBs and detectable BBHs form at different redshifts and metallicities, with detectable HMXBs forming at much lower redshifts and higher metallicities than detectable BBHs. We also find disparities in the mass distributions of these populations, with detectable merging BBH progenitors pulling to higher component masses relative to the full detectable HMXB population. Fewer than 3% of detectable HMXBs host BHs >35M_⊙in our simulated populations. Furthermore, we find the probability that a detectable HMXB will merge as a BBH system within a Hubble time is ≃0.6%. Thus, it is unsurprising that no currently observed HMXB is predicted to form a merging BBH with high probability. 

Abstract Gravitational-wave observations of binary black hole (BBH) systems point to black hole spin magnitudes being relatively low. These measurements appear in tension with high spin measurements for high-mass X-ray binaries (HMXBs). We use grids of MESA simulations combined with the rapid population-synthesis code COSMIC to examine the origin of these two binary populations. It has been suggested that Case-A mass transfer while both stars are on the main sequence can form high-spin BHs in HMXBs. Assuming this formation channel, we show that depending on the critical mass ratios for the stability of mass transfer, 48%–100% of these Case-A HMXBs merge during the common-envelope phase and up to 42% result in binaries too wide to merge within a Hubble time. Both MESA and COSMIC show that high-spin HMXBs formed through Case-A mass transfer can only form merging BBHs within a small parameter space where mass transfer can lead to enough orbital shrinkage to merge within a Hubble time. We find that only up to 11% of these Case-A HMXBs result in BBH mergers, and at most 20% of BBH mergers came from Case-A HMXBs. Therefore, it is not surprising that these two spin distributions are observed to be different. 

{"Abstract":["This dataset contains machine learning and volunteer classifications from the Gravity Spy project. It includes glitches from observing runs O1, O2, O3a and O3b that received at least one classification from a registered volunteer in the project. It also indicates glitches that are nominally retired from the project using our default set of retirement parameters, which are described below. See more details in the Gravity Spy Methods paper. <\/p>\n\nWhen a particular subject in a citizen science project (in this case, glitches from the LIGO datastream) is deemed to be classified sufficiently it is "retired" from the project. For the Gravity Spy project, retirement depends on a combination of both volunteer and machine learning classifications, and a number of parameterizations affect how quickly glitches get retired. For this dataset, we use a default set of retirement parameters, the most important of which are: <\/p>\n\nA glitches must be classified by at least 2 registered volunteers<\/li>Based on both the initial machine learning classification and volunteer classifications, the glitch has more than a 90% probability of residing in a particular class<\/li>Each volunteer classification (weighted by that volunteer's confusion matrix) contains a weight equal to the initial machine learning score when determining the final probability<\/li><\/ol>\n\nThe choice of these and other parameterization will affect the accuracy of the retired dataset as well as the number of glitches that are retired, and will be explored in detail in an upcoming publication (Zevin et al. in prep). <\/p>\n\nThe dataset can be read in using e.g. Pandas: \n```\nimport pandas as pd\ndataset = pd.read_hdf('retired_fulldata_min2_max50_ret0p9.hdf5', key='image_db')\n```\nEach row in the dataframe contains information about a particular glitch in the Gravity Spy dataset. <\/p>\n\nDescription of series in dataframe<\/strong><\/p>\n\n['1080Lines', '1400Ripples', 'Air_Compressor', 'Blip', 'Chirp', 'Extremely_Loud', 'Helix', 'Koi_Fish', 'Light_Modulation', 'Low_Frequency_Burst', 'Low_Frequency_Lines', 'No_Glitch', 'None_of_the_Above', 'Paired_Doves', 'Power_Line', 'Repeating_Blips', 'Scattered_Light', 'Scratchy', 'Tomte', 'Violin_Mode', 'Wandering_Line', 'Whistle']\n\tMachine learning scores for each glitch class in the trained model, which for a particular glitch will sum to unity<\/li><\/ul>\n\t<\/li>['ml_confidence', 'ml_label']\n\tHighest machine learning confidence score across all classes for a particular glitch, and the class associated with this score<\/li><\/ul>\n\t<\/li>['gravityspy_id', 'id']\n\tUnique identified for each glitch on the Zooniverse platform ('gravityspy_id') and in the Gravity Spy project ('id'), which can be used to link a particular glitch to the full Gravity Spy dataset (which contains GPS times among many other descriptors)<\/li><\/ul>\n\t<\/li>['retired']\n\tMarks whether the glitch is retired using our default set of retirement parameters (1=retired, 0=not retired)<\/li><\/ul>\n\t<\/li>['Nclassifications']\n\tThe total number of classifications performed by registered volunteers on this glitch<\/li><\/ul>\n\t<\/li>['final_score', 'final_label']\n\tThe final score (weighted combination of machine learning and volunteer classifications) and the most probable type of glitch<\/li><\/ul>\n\t<\/li>['tracks']\n\tArray of classification weights that were added to each glitch category due to each volunteer's classification<\/li><\/ul>\n\t<\/li><\/ul>\n\n <\/p>\n\n```\nFor machine learning classifications on all glitches in O1, O2, O3a, and O3b, please see Gravity Spy Machine Learning Classifications on Zenodo<\/p>\n\nFor the most recently uploaded training set used in Gravity Spy machine learning algorithms, please see Gravity Spy Training Set on Zenodo.<\/p>\n\nFor detailed information on the training set used for the original Gravity Spy machine learning paper, please see Machine learning for Gravity Spy: Glitch classification and dataset on Zenodo. <\/p>"]}