Unlike traditional backdoor attacks that focus on specific class labels, our approach aims to induce poisoned models to predict future data as a predefined target pattern.

Unlike traditional backdoor attacks that focus on specific class labels, our approach aims to induce poisoned models to predict future data as a predefined target pattern.

Nevertheless, Query-Key Norm remains promisingly convergent with SDM's requirement of "Sparse Distributed Memory (SDM), is a biologically plausible form of associative memory". For each layer we take the maximum softmax input for a given text prompt for each head. We then take the mean of this maximum for each head and plot this for each text input. Hamming distances that read to and write from fewer patterns. Small and Large models aggregated across all text data for all heads and layers.

Metasurfaces are ultra-thin optical elements composed of engineered sub-wavelength structures that enable precise control of light. Their inverse design - determining a geometry that yields a desired optical response - is challenging due to the complex, nonlinear relationship between structure and optical properties. This often requires expert tuning, is prone to local minima, and involves significant computational overhead. In this work, we address these challenges by integrating the generative capabilities of diffusion models into computational design workflows. Using an RCWA simulator, we generate training data consisting of metasurface geometries and their corresponding far-field scattering patterns. We then train a conditional diffusion model to predict meta-atom geometry and height from a target spatial power distribution at a specified wavelength, sampled from a continuous supported band. Once trained, the model can generate metasurfaces with low error, either directly using RCWA-guided posterior sampling or by serving as an initializer for traditional optimization methods. We demonstrate our approach on the design of a spatially uniform intensity splitter and a polarization beam splitter, both produced with low error in under 30 minutes. To support further research in data-driven metasurface design, we publicly release our code and datasets.

This paper introduces Differentiable Logic Cellular Automata (DiffLogic CA), a novel combination of Neural Cellular Automata (NCA) and Differentiable Logic Gates Networks (DLGNs). The fundamental computation units of the model are differentiable logic gates, combined into a circuit. During training, the model is fully end-to-end differentiable allowing gradient-based training, and at inference time it operates in a fully discrete state space. This enables learning local update rules for cellular automata while preserving their inherent discrete nature. We demonstrate the versatility of our approach through a series of milestones: (1) fully learning the rules of Conway's Game of Life, (2) generating checkerboard patterns that exhibit resilience to noise and damage, (3) growing a lizard shape, and (4) multi-color pattern generation. Our model successfully learns recurrent circuits capable of generating desired target patterns. For simpler patterns, we observe success with both synchronous and asynchronous updates, demonstrating significant generalization capabilities and robustness to perturbations. We make the case that this combination of DLGNs and NCA represents a step toward programmable matter and robust computing systems that combine binary logic, neural network adaptability, and localized processing. This work, to the best of our knowledge, is the first successful application of differentiable logic gate networks in recurrent architectures.

Trajectory data, which tracks movements through geographic locations, is crucial for improving real-world applications. However, collecting such sensitive data raises considerable privacy concerns. Local differential privacy (LDP) offers a solution by allowing individuals to locally perturb their trajectory data before sharing it. Despite its privacy benefits, LDP protocols are vulnerable to data poisoning attacks, where attackers inject fake data to manipulate aggregated results. In this work, we make the first attempt to analyze vulnerabilities in several representative LDP trajectory protocols. We propose \textsc{TraP}, a heuristic algorithm for data \underline{P}oisoning attacks using a prefix-suffix method to optimize fake \underline{Tra}jectory selection, significantly reducing computational complexity. Our experimental results demonstrate that our attack can substantially increase target pattern occurrences in the perturbed trajectory dataset with few fake users. This study underscores the urgent need for robust defenses and better protocol designs to safeguard LDP trajectory data against malicious manipulation.

The persistent and graded activity often observed in cortical circuits is sometimes seen as a signature of autoassociative retrieval of memories stored earlier in synaptic efficacies. However, despite decades of theoretical work on the subject, the mechanisms that support the storage and retrieval of memories remain unclear. Previous proposals concerning the dynamics of memory networks have fallen short of incorporating some key physiological constraints in a unified way. Specifically, some models violate Dale's law (i.e.

In the realm of lithography, Optical Proximity Correction (OPC) is a crucial resolution enhancement technique that optimizes the transmission function of photomasks on a pixel-based to effectively counter Optical Proximity Effects (OPE). However, conventional pixel-based OPC methods often generate patterns that pose manufacturing challenges, thereby leading to the increased cost in practical scenarios. This paper presents a novel inverse lithographic approach to OPC, employing a model-driven, block stacking deep learning framework that expedites the generation of masks conducive to manufacturing. This method is founded on vector lithography modelling and streamlines the training process by eliminating the requirement for extensive labeled datasets. Furthermore, diversity of mask patterns is enhanced by employing a wave function collapse algorithm, which facilitates the random generation of a multitude of target patterns, therefore significantly expanding the range of mask paradigm. Numerical experiments have substantiated the efficacy of the proposed end-to-end approach, highlighting its superior capability to manage mask complexity within the context of advanced OPC lithography. This advancement is anticipated to enhance the feasibility and economic viability of OPC technology within actual manufacturing environments.

Patterns arise spontaneously in a range of systems spanning the sciences, and their study typically focuses on mechanisms to understand their evolution in space-time. Increasingly, there has been a transition towards controlling these patterns in various functional settings, with implications for engineering. Here, we combine our knowledge of a general class of dynamical laws for pattern formation in non-equilibrium systems, and the power of stochastic optimal control approaches to present a framework that allows us to control patterns at multiple scales, which we dub the "Hamiltonian bridge". We use a mapping between stochastic many-body Lagrangian physics and deterministic Eulerian pattern forming PDEs to leverage our recent approach utilizing the Feynman-Kac-based adjoint path integral formulation for the control of interacting particles and generalize this to the active control of patterning fields. We demonstrate the applicability of our computational framework via numerical experiments on the control of phase separation with and without a conserved order parameter, self-assembly of fluid droplets, coupled reaction-diffusion equations and finally a phenomenological model for spatio-temporal tissue differentiation. We interpret our numerical experiments in terms of a theoretical understanding of how the underlying physics shapes the geometry of the pattern manifold, altering the transport paths of patterns and the nature of pattern interpolation. We finally conclude by showing how optimal control can be utilized to generate complex patterns via an iterative control protocol over pattern forming pdes which can be casted as gradient flows. All together, our study shows how we can systematically build in physical priors into a generative framework for pattern control in non-equilibrium systems across multiple length and time scales.

Multivariate Time Series (MTS) forecasting is a fundamental task with numerous real-world applications, such as transportation, climate, and epidemiology. While a myriad of powerful deep learning models have been developed for this task, few works have explored the robustness of MTS forecasting models to malicious attacks, which is crucial for their trustworthy employment in high-stake scenarios. To address this gap, we dive deep into the backdoor attacks on MTS forecasting models and propose an effective attack method named BackTime.By subtly injecting a few stealthy triggers into the MTS data, BackTime can alter the predictions of the forecasting model according to the attacker's intent. Specifically, BackTime first identifies vulnerable timestamps in the data for poisoning, and then adaptively synthesizes stealthy and effective triggers by solving a bi-level optimization problem with a GNN-based trigger generator. Extensive experiments across multiple datasets and state-of-the-art MTS forecasting models demonstrate the effectiveness, versatility, and stealthiness of \method{} attacks. The code is available at \url{https://github.com/xiaolin-cs/BackTime}.