Auditing the use of data in training machine-learning (ML) models is an increasingly pressing challenge, as myriad ML practitioners routinely leverage the effort of content creators to train models without their permission. In this paper, we propose a general method to audit an ML model for the use of a data-owner's data in training, without prior knowledge of the ML task for which the data might be used. Our method leverages any existing black-box membership inference method, together with a sequential hypothesis test of our own design, to detect data use with a quantifiable, tunable false-detection rate. We show the effectiveness of our proposed framework by applying it to audit data use in two types of ML models, namely image classifiers and foundation models.

We study the effects of injecting human-generated designs into the initial population of an evolutionary robotics experiment, where subsequent population of robots are optimised via a Genetic Algorithm and MAP-Elites. First, human participants interact via a graphical front-end to explore a directly-parameterised legged robot design space and attempt to produce robots via a combination of intuition and trial-and-error that perform well in a range of environments. Environments are generated whose corresponding high-performance robot designs range from intuitive to complex and hard to grasp. Once the human designs have been collected, their impact on the evolutionary process is assessed by replacing a varying number of designs in the initial population with human designs and subsequently running the evolutionary algorithm. Our results suggest that a balance of random and hand-designed initial solutions provides the best performance for the problems considered, and that human designs are most valuable when the problem is intuitive. The influence of human design in an evolutionary algorithm is a highly understudied area, and the insights in this paper may be valuable to the area of AI-based design more generally.

Alternating direction method of multipliers (ADMM) is a widely used tool for machine learning in distributed settings where a machine learning model is trained over distributed data sources through an interactive process of local computation and message passing. Such an iterative process could cause privacy concerns of data owners. The goal of this paper is to provide differential privacy for ADMM-based distributed machine learning. Prior approaches on differentially private ADMM exhibit low utility under high privacy guarantee and assume the objective functions of the learning problems to be smooth and strongly convex. To address these concerns, we propose a novel differentially private ADMM-based distributed learning algorithm called DP-ADMM, which combines an approximate augmented Lagrangian function with time-varying Gaussian noise addition in the iterative process to achieve higher utility for general objective functions under the same differential privacy guarantee. We also apply the moments accountant method to analyze the end-to-end privacy loss. The theoretical analysis shows that the DP-ADMM can be applied to a wider class of distributed learning problems, is provably convergent, and offers an explicit utility-privacy tradeoff. To our knowledge, this is the first paper to provide explicit convergence and utility properties for differentially private ADMM-based distributed learning algorithms. The evaluation results demonstrate that our approach can achieve good convergence and model accuracy under high end-to-end differential privacy guarantee.

Nowadays most mobile devices are equipped with advanced sensors, enabling the measurement of information about surrounding environment or social settings. The ubiquity of mobile devices makes them the perfect platform for massive data collection, which motivates the emergence of mobile crowdsensing paradigm. However, due to the inherent noisy nature of the sensing process and the limited capability of low-cost commodity sensors, crowdsensed information tends to be less reliable compared with sensing results through dedicated sensing hardware, and multiple crowdsensing sources may conflict with each other. Thus, it is important to resolve conflicts in the collected data and discover the underlying truth. Traditional truth discovery approaches usually estimate the reliability of data sources and predict the truth value based on source reliability. However, recent data poisoning attacks greatly degrade the performance of existing truth discovery algorithms, where attackers aim to maximize the utility loss. In this paper, we investigate the data poisoning attacks on truth discovery and propose a robust approach against such attacks through additional source estimation and source filtering before data aggregation. Based on real-world data, we simulate our approach and evaluate its performance under data poisoning attacks, demonstrating the robustness of our approach.

The representation of the environment strongly affects how robots can move and interact with it. This paper presents an online approach for continuous mapping using Gaussian Process Implicit Surfaces (GPISs). Compared with grid-based methods, GPIS better utilizes sparse measurements to represent the world seamlessly. It provides direct access to the signed-distance function (SDF) and its derivatives which are invaluable for other robotic tasks and it incorporates uncertainty in the sensor measurements. Our approach incrementally and efficiently updates GPIS by employing a regressor on observations and a spatial tree structure. The effectiveness of the suggested approach is demonstrated using simulations and real world 2D/3D data.

This paper reviews at first the features of the present information techniques including the telephone, the television, the computer, and the body sensor network briefly. Then, the concept and the construction of microelectronic neural bridges (MENB) are discussed. A special animal experiment in which the signal regeneration and the function rebuilding were realized by using a MENB between two far-separated nervous systems is demonstrated. The applications of presented concept are prospected.