Huajie Chen

Huajie Chen, Tianqing Zhu, Lefeng Zhang et al.

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query results as the ground-truth labels, an adversary can steal a piracy model with performance comparable to the original model. Two key issues that cause the threat are, on the one hand, accurate and unlimited queries can be obtained by the adversary; on the other hand, the adversary can aggregate the query results to train the model step by step. The existing defenses usually employ model watermarking or fingerprinting to protect the ownership. However, these methods cannot proactively prevent the violation from happening. To mitigate the threat, we propose QUEEN (QUEry unlEarNing) that proactively launches counterattacks on potential model extraction attacks from the very beginning. To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance. In sensitivity measurement, QUEEN measures the single query sensitivity by its distance from the center of its cluster in the feature space. To reduce the learning accuracy of attacks, for the highly sensitive query batch, QUEEN applies query unlearning, which is implemented by gradient reverse to perturb the softmax output such that the piracy model will generate reverse gradients to worsen its performance unconsciously. Experiments show that QUEEN outperforms the state-of-the-art defenses against various model extraction attacks with a relatively low cost to the model accuracy. The artifact is publicly available at https://anonymous.4open.science/r/queen implementation-5408/.

Ilyes Batatia, Lars L. Schaaf, Huajie Chen et al.

Graph Neural Networks (GNNs), especially message-passing neural networks (MPNNs), have emerged as powerful architectures for learning on graphs in diverse applications. However, MPNNs face challenges when modeling non-local interactions in graphs such as large conjugated molecules, and social networks due to oversmoothing and oversquashing. Although Spectral GNNs and traditional neural networks such as recurrent neural networks and transformers mitigate these challenges, they often lack generalizability, or fail to capture detailed structural relationships or symmetries in the data. To address these concerns, we introduce Matrix Function Neural Networks (MFNs), a novel architecture that parameterizes non-local interactions through analytic matrix equivariant functions. Employing resolvent expansions offers a straightforward implementation and the potential for linear scaling with system size. The MFN architecture achieves stateof-the-art performance in standard graph benchmarks, such as the ZINC and TU datasets, and is able to capture intricate non-local interactions in quantum systems, paving the way to new state-of-the-art force fields.

Yizhe Xie, Congcong Zhu, Xinyue Zhang et al.

Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccuracies to gradually solidify into system-level false consensus through iteration. Such risks are difficult to trace since errors can propagate and amplify through message dependencies. Existing protections often rely on single-agent validation or require modifications to the collaboration architecture, which can weaken effective information flow and may not align with natural collaboration processes in real tasks. To address this, we propose a propagation dynamics model tailored for LLM-MAS that abstracts collaboration as a directed dependency graph and provides an early-stage risk criterion to characterize amplification risk. Through experiments on six mainstream frameworks, we identify three vulnerability classes: cascade amplification, topological sensitivity, and consensus inertia. We further instantiate an attack where injecting just a single atomic error seed leads to widespread failure. In response, we introduce a genealogy-graph-based governance layer, implemented as a message-layer plugin, that suppresses both endogenous and exogenous error amplification without altering the collaboration architecture. Experiments show that this approach raises the defense success rate from a baseline of 0.32 to over 0.89 and significantly mitigates the cascading spread of minor errors.

Huajie Chen, Faizan Q. Nazar, Christoph Ortner

We develop a rigorous framework for modelling the geometry equilibration of crystalline defects. We formulate the equilibration of crystal defects as a variational problems on a discrete energy space and establish qualitatively sharp far-field decay estimates for the equilibrium configuration. This work extends Ehrlacher, Ortner, Shapeev (2016) by admitting infinite-range interaction which in particular includes some quantum chemistry based interatomic potentials.

Huajie Chen, Jianfeng Lu, Christoph Ortner

We consider a tight binding model for localised crystalline defects with electrons in the canonical ensemble (finite electronic temperature) and nuclei positions relaxed according to the Born--Oppenheimer approximation. We prove that the limit model as the computational domain size grows to infinity is formulated in the grand-canonical ensemble for the electrons. The Fermi-level for the limit model is fixed at a homogeneous crystal level, independent of the defect or electron number in the sequence of finite-domain approximations. We quantify the rates of convergence for the nuclei configuration and for the Fermi-level.

Huajie Chen, Christoph Ortner

QM/MM hybrid methods employ accurate quantum (QM) models only in regions of interest (defects) and switch to computationally cheaper interatomic potential (MM) models to describe the crystalline bulk. We develop two QM/MM hybrid methods for crystalline defect simulations, an energy-based and a force-based formulation, employing a tight binding QM model. Both methods build on two principles: (i) locality of the QM model; and (ii) constructing the MM model as an explicit and controllable approximation of the QM model. This approach enables us to establish explicit convergence rates in terms of the size of QM region.

Huajie Chen, Gero Friesecke

The exact interaction energy of a many-electron system is determined by the electron pair density, which is not well-approximated in standard Kohn-Sham density functional models. Here we study the (complicated but well-defined) exact universal map from density to pair density. We survey how many common functionals, including the most basic version of the LDA (Dirac exchange with no correlation contribution), arise from particular approximations of this map. We develop an algorithm to compute the map numerically, and apply it to one-parameter families {a*rho(a*x)} of one-dimensional homogeneous and inhomogeneous single-particle densities. We observe that the pair density develops remarkable multiscale patterns which strongly depend on both the particle number and the "width" 1/a of the single-particle density. The simulation results are confirmed by rigorous asymptotic results in the limiting regimes a>>1 and a<<1. For one-dimensional homogeneous systems, we show that the whole spectrum of patterns is reproduced surprisingly well by a simple asymptotics-based ansatz which slowly smoothens out the "strictly correlated" a=0 pair density while slowly turning on the a=infty "exchange" terms as a increases. Our findings lend theoretical support to the celebrated semi-empirical idea [Becke93] to mix in a fractional amount of exchange, albeit not to assuming the mixing to be additive and taking the fraction to be a system independent constant.

Huajie Chen, Christoph Ortner

The tight binding model is a minimal electronic structure model for molecular modelling and simulation. We show that the total energy in this model can be decomposed into site energies, that is, into contributions from each atomic site whose influence on their environment decays exponentially. This result lays the foundation for a rigorous analysis of QM/MM coupling schemes.