Concept Enhancement Engineering: A Lightweight and Efficient Robust Defense Against Jailbreak Attacks in Embodied AI

Embodied Intelligence (EI) systems integrated with large language models (LLMs) face significant security risks, particularly from jailbreak attacks that manipulate models into generating harmful outputs or executing unsafe physical actions. Traditional defense strategies, such as input filtering and output monitoring, often introduce high computational overhead or interfere with task performance in real-time embodied scenarios. To address these challenges, we propose Concept Enhancement Engineering (CEE), a novel defense framework that leverages representation engineering to enhance the safety of embodied LLMs by dynamically steering their internal activations. CEE operates by (1) extracting multilingual safety patterns from model activations, (2) constructing control directions based on safety-aligned concept subspaces, and (3) applying subspace concept rotation to reinforce safe behavior during inference. Our experiments demonstrate that CEE effectively mitigates jailbreak attacks while maintaining task performance, outperforming existing defense methods in both robustness and efficiency. This work contributes a scalable and interpretable safety mechanism for embodied AI, bridging the gap between theoretical representation engineering and practical security applications. Our findings highlight the potential of latent-space interventions as a viable defense paradigm against emerging adversarial threats in physically grounded AI systems.

Dendritic Localized Learning: Toward Biologically Plausible Algorithm

Backpropagation is the foundational algorithm for training neural networks and a key driver of deep learning's success. However, its biological plausibility has been challenged due to three primary limitations: weight symmetry, reliance on global error signals, and the dual-phase nature of training, as highlighted by the existing literature. Although various alternative learning approaches have been proposed to address these issues, most either fail to satisfy all three criteria simultaneously or yield suboptimal results. Inspired by the dynamics and plasticity of pyramidal neurons, we propose Dendritic Localized Learning (DLL), a novel learning algorithm designed to overcome these challenges. Extensive empirical experiments demonstrate that DLL satisfies all three criteria of biological plausibility while achieving state-of-the-art performance among algorithms that meet these requirements. Furthermore, DLL exhibits strong generalization across a range of architectures, including MLPs, CNNs, and RNNs. These results, benchmarked against existing biologically plausible learning algorithms, offer valuable empirical insights for future research. We hope this study can inspire the development of new biologically plausible algorithms for training multilayer networks and advancing progress in both neuroscience and machine learning.

FedLEC: Effective Federated Learning Algorithm with Spiking Neural Networks Under Label Skews

With the advancement of neuromorphic chips, implementing Federated Learning (FL) with Spiking Neural Networks (SNNs) potentially offers a more energy-efficient schema for collaborative learning across various resource-constrained edge devices. However, one significant challenge in the FL systems is that the data from different clients are often non-independently and identically distributed (non-IID), with label skews presenting substantial difficulties in various federated SNN learning tasks. In this study, we propose a practical post-hoc framework named FedLEC to address the challenge. This framework penalizes the corresponding local logits for locally missing labels to enhance each local model's generalization ability. Additionally, it leverages the pertinent label distribution information distilled from the global model to mitigate label bias. Extensive experiments with three different structured SNNs across five datasets (i.e., three non-neuromorphic and two neuromorphic datasets) demonstrate the efficiency of FedLEC. Compared to seven state-of-the-art FL algorithms, FedLEC achieves an average accuracy improvement of approximately 11.59\% under various label skew distribution settings.

THz Channels for Short-Range Mobile Networks: Multipath Clusters and Human Body Shadowing

The THz band (0.1-10 THz) is emerging as a crucial enabler for sixth-generation (6G) mobile communication systems, overcoming the limitations of current technologies and unlocking new opportunities for low-latency and ultra-high-speed communications by utilizing several tens of GHz transmission bandwidths. However, extremely high spreading losses and other interaction losses pose significant challenges to establishing wide-area communication coverage, while human body shadowing further complicates maintaining stable communication links. Although point-to-point (P2P) fixed wireless access in the THz band has been successfully demonstrated, realizing fully mobile and reliable wireless access remains a challenge due to numerous issues to be solved for highly directional communication. To provide insights into the design of THz communication systems, this article addresses the challenges associated with THz short-range mobile access networks. It offers an overview of recent findings on the environment-dependence of multipath cluster channel properties and the impact of human body shadowing, based on measurements at 300 GHz using a double-directional high-resolution channel sounder and a motion capture-integrated channel sounder.

Information-Theoretic Generative Clustering of Documents

We present {\em generative clustering} (GC) for clustering a set of documents, $\mathrm{X}$, by using texts $\mathrm{Y}$ generated by large language models (LLMs) instead of by clustering the original documents $\mathrm{X}$. Because LLMs provide probability distributions, the similarity between two documents can be rigorously defined in an information-theoretic manner by the KL divergence. We also propose a natural, novel clustering algorithm by using importance sampling. We show that GC achieves the state-of-the-art performance, outperforming any previous clustering method often by a large margin. Furthermore, we show an application to generative document retrieval in which documents are indexed via hierarchical clustering and our method improves the retrieval accuracy.

Efficient Joint Precoding Design for Wideband Intelligent Reflecting Surface-Assisted Cell-Free Network

In this paper, we propose an efficient joint precoding design method to maximize the weighted sum-rate in wideband intelligent reflecting surface (IRS)-assisted cell-free networks by jointly optimizing the active beamforming of base stations and the passive beamforming of IRS. Due to employing wideband transmissions, the frequency selectivity of IRSs has to been taken into account, whose response usually follows a Lorentzian-like profile. To address the high-dimensional non-convex optimization problem, we employ a fractional programming approach to decouple the non-convex problem into subproblems for alternating optimization between active and passive beamforming. The active beamforming subproblem is addressed using the consensus alternating direction method of multipliers (CADMM) algorithm, while the passive beamforming subproblem is tackled using the accelerated projection gradient (APG) method and Flecher-Reeves conjugate gradient method (FRCG). Simulation results demonstrate that our proposed approach achieves significant improvements in weighted sum-rate under various performance metrics compared to primal-dual subgradient (PDS) with ideal reflection matrix. This study provides valuable insights for computational complexity reduction and network capacity enhancement.

An Asynchronous Multi-core Accelerator for SNN inference

Spiking Neural Networks (SNNs) are extensively utilized in brain-inspired computing and neuroscience research. To enhance the speed and energy efficiency of SNNs, several many-core accelerators have been developed. However, maintaining the accuracy of SNNs often necessitates frequent explicit synchronization among all cores, which presents a challenge to overall efficiency. In this paper, we propose an asynchronous architecture for Spiking Neural Networks (SNNs) that eliminates the need for inter-core synchronization, thus enhancing speed and energy efficiency. This approach leverages the pre-determined dependencies of neuromorphic cores established during compilation. Each core is equipped with a scheduler that monitors the status of its dependencies, allowing it to safely advance to the next timestep without waiting for other cores. This eliminates the necessity for global synchronization and minimizes core waiting time despite inherent workload imbalances. Comprehensive evaluations using five different SNN workloads show that our architecture achieves a 1.86x speedup and a 1.55x increase in energy efficiency compared to state-of-the-art synchronization architectures.

Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals

Semi-supervised anomaly detection for sensor signals is critical in ensuring system reliability in smart manufacturing. However, existing methods rely heavily on data correlation, neglecting causality and leading to potential misinterpretations due to confounding factors. Moreover, while current reinforcement learning-based methods can effectively identify known and unknown anomalies with limited labeled samples, these methods still face several challenges, such as under-utilization of priori knowledge, lack of model flexibility, and deficient reward feedback during environmental interactions. To address the above problems, this paper innovatively constructs a counterfactual causal reinforcement learning model, termed Triple-Assisted Causal Reinforcement Learning Anomaly Detector (Tri-CRLAD). The model leverages causal inference to extract the intrinsic causal feature in data, enhancing the agent's utilization of prior knowledge and improving its generalization capability. In addition, Tri-CRLAD features a triple decision support mechanism, including a sampling strategy based on historical similarity, an adaptive threshold smoothing adjustment strategy, and an adaptive decision reward mechanism. These mechanisms further enhance the flexibility and generalization ability of the model, enabling it to effectively respond to various complex and dynamically changing environments. Experimental results across seven diverse sensor signal datasets demonstrate that Tri-CRLAD outperforms nine state-of-the-art baseline methods. Notably, Tri-CRLAD achieves up to a 23\% improvement in anomaly detection stability with minimal known anomaly samples, highlighting its potential in semi-supervised anomaly detection scenarios. Our code is available at https://github.com/Aoudsung/Tri-CRLAD.

Correlation Dimension of Natural Language in a Statistical Manifold

The correlation dimension of natural language is measured by applying the Grassberger-Procaccia algorithm to high-dimensional sequences produced by a large-scale language model. This method, previously studied only in a Euclidean space, is reformulated in a statistical manifold via the Fisher-Rao distance. Language exhibits a multifractal, with global self-similarity and a universal dimension around 6.5, which is smaller than those of simple discrete random sequences and larger than that of a Barab\'asi-Albert process. Long memory is the key to producing self-similarity. Our method is applicable to any probabilistic model of real-world discrete sequences, and we show an application to music data.

Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training

Temporal grounding is crucial in multimodal learning, but it poses challenges when applied to animal behavior data due to the sparsity and uniform distribution of moments. To address these challenges, we propose a novel Positional Recovery Training framework (Port), which prompts the model with the start and end times of specific animal behaviors during training. Specifically, Port enhances the baseline model with a Recovering part to predict flipped label sequences and align distributions with a Dual-alignment method. This allows the model to focus on specific temporal regions prompted by ground-truth information. Extensive experiments on the Animal Kingdom dataset demonstrate the effectiveness of Port, achieving an IoU@0.3 of 38.52. It emerges as one of the top performers in the sub-track of MMVRAC in ICME 2024 Grand Challenges.