Evaluating the safety robustness of LLMs is critical for their deployment.However, mainstream Red Teaming methods rely on online generation and black-box output analysis.These approaches are not only costly but also suffer from feedback latency, making them unsuitable for agile diagnostics after training a new model.To address this, we propose N-GLARE (A Non-Generative, Latent Representation-Efficient LLM Safety Evaluator).N-GLARE operates entirely on the model's latent representations, bypassing the need for full text generation.It characterizes hidden layer dynamics by analyzing the APT (Angular-Probabilistic Trajectory) of latent representations and introducing the JSS (Jensen-Shannon Separability) metric.Experiments on over 40 models and 20 red teaming strategies demonstrate that the JSS metric exhibits high consistency with Red Teaming safety rankings at less than 1% token and runtime cost.

Spiking Neural Network (SNN) simulation involves emulating the activation and firing of spiking neurons on hardware platforms. This is a highly time-sensitive task, requiring the simulation of billions of neurons and their intercommunication within a few milliseconds. Each neuron performs a complex, interdependent multi-stage communication and computation task. We consider the task placement of SNN on supercomputers to accelerate SNN simulation. Existing task placement methods for SNN simulations have two major limitations. First, they lack the capability to handle large-scale SNNs with billions of neurons. Second, they focus primarily on optimizing communication delay, while neglecting multi-stage computation delays in SNN simulations. In this paper, we formalize the SNN Joint Multi-stage Communication and Computation Placement (SJCCP) problem. We demonstrate that SJCCP can be solved using an approximation algorithm with an approximation ratio of $O\left( {{k^2}\sqrt {\log n\log k} } \right)$, where n is the number of voxels in the SNN and k is the number of GPUs. To further reduce the time complexity of solving SJCCP in practice, we propose a novel efficient framework, FastSJP, tailored for large-scale SNN placement. Then we apply the FastSJP framework to a human brain simulation that runs a large-scale SNN model derived from authentic biological data on a supercomputer equipped with 1024 GPUs. Experimental results verify that our framework notably reduces time overhead, ranging from 17.31% to 28.45%, compared to state-of-the-art methods. Leveraging the computational power of the supercomputer, FastSJP maximizes the problem size and processing performance, significantly advancing the development of brain-inspired intelligence.

Brain simulation is an inherently highly parallel and time-sensitive task, requiring the simulation of billions of neurons and their interactions within just a few milliseconds. With the growing availability of brain data from biological research, more realistic and detailed simulations are becoming feasible. However, this also poses unprecedented challenges for parallel computing due to the extreme sparsity and heterogeneity of the emerging workloads. Efficient deployment of such workloads on modern HPC systems is critical to overcoming these challenges. We propose BMapper, a deployment framework that enables efficient parallel execution of brain simulations on supercomputers. BMapper comprises three synergistic components: BPartitioning, which introduces a novel multi-dimensional hybrid partitioning strategy to balance workloads across GPUs and reduce inter-GPU spike traffic; BPlacement, which applies deterministic spectral partitioning to minimize inter-server communication; and BRelaying, which identifies lightly loaded GPUs to assist the top-k heavily loaded ones by relaying spike traffic. These components work together to balance loads and minimize communication overhead, enabling high-speed simulation of large-scale brain models. BMapper has been deployed to simulate up to 10 billion neurons on a 1000-GPU supercomputer, achieving 25.15%–47.48% faster execution than state-of-the-art methods.

Vertical Federated Learning (VFL) enables collaborative machine learning without the need for participants to share their raw private data. However, recent studies have uncovered privacy risks, where adversaries might reconstruct sensitive features through data leakage during the learning process. Al-though existing data reconstruction methods are effective to some extent, they exhibit limitations in VFL scenarios, as initiating an attack requires meeting more stringent conditions. To gain a comprehensive understanding of the risks of data reconstruction in VFL, this paper proposes a unified framework, the Unified InverNet Framework in VFL (UIFV), for data reconstruction under realistic black-box threat models. Within the UIFV framework, we consider four attack scenarios, strictly adhering to VFL protocols to maintain confidentiality. Experiments on four datasets show that our methods significantly outperform state-of-the-art techniques in terms of applicability and attack precision. Our work reveals severe privacy vulnerabilities within VFL systems that pose real threats to practical VFL applications, thus confirming the necessity of further enhancing privacy protection in the VFL architecture. Overall, this paper provides a thorough analysis of the risks of data reconstruction in VFL and offers important guidance to enhance the security of VFL deployments.

The predominant authentication method still relies on usernames and passwords. To enhance memorability, domain terms may have been opted to include as part of passwords. However, there is little analysis of the extent to which such practice affects password security, so there is a lack of guidance on how users use domain terms on websites with different domain characteristics. To address the problem, we propose a novel approach to analyze the security effect of using domain terms in passwords. The methodology primarily consists of three stages. First, we utilize Web crawlers to harvest domain vocabularies, subsequently leveraging the TextRank algorithm to rank their importance. Second, we propose an algorithm for constructing a simulated domain-specific password dataset by replacing password elements with domain terms. Third, password guessing experiments are done on the dataset using PCFG (Probabilistic Context-Free Grammar) and the Markov model to evaluate the impact of domain terms on password security. The experimental results indicate that, for systems without clear domain, 20% domain terms replacement in the test set can reduce the cracking rate by up to 5.45%. In contrast, for domain-specific systems, 20% domain terms replacement in the training set can increase the cracking rate by 6.45%. These findings provide practical guidance on the application of domain knowledge in password creation for different types of systems. In summary, this study offers a novel perspective for exploring the security implications of passwords influenced by specific domains.