Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation.Previous detection methods, including finetuned small models or LLM-based detectors, often struggle with its dynamically evolving nature.In this work, we propose a novel framework called the Symbolic Adversarial Learning Framework (SALF), which implements an adversarial training paradigm by an agent symbolic learning optimization process, rather than relying on numerical updates.SALF introduces a paradigm where the generation agent crafts deceptive narratives, and the detection agent uses structured debates to identify logical and factual flaws for detection, and they iteratively refine themselves through such adversarial interactions.Unlike traditional neural updates, we represent agents using agent symbolic learning, where learnable weights are defined by agent prompts, and simulate back-propagation and gradient descent by operating on natural language representations of weights, loss, and gradients.Experiments on two multilingual benchmark datasets demonstrate SALF's effectiveness, showing it generates sophisticated fake news that degrades state-of-the-art detection performance by up to 53.4% in Chinese and 34.2% in English on average.SALF also refines detectors, improving detection of refined content by up to 7.7%.We hope our work inspires further exploration into more robust, adaptable fake news detection systems.

Generative Adversarial Networks (GANs) are powerful tools for generating synthetic data, making them highly valuable in data-driven research by addressing data scarcity/imbalance in real-world datasets. However, GANs often suffer from mode collapse, where the generator produces a limited range of outputs, failing to capture the full diversity of the target distribution. While the Wasserstein GAN (WGAN) improves training stability and mitigates mode collapse compared to traditional GANs, it is not entirely immune to this issue. In this paper, we propose an Entropy-Augmented WGAN (E-WGAN), which incorporates an additional entropy-based information into the generator's loss function to explicitly promote diversity in generated samples. By maximizing the entropy of the generator's output distribution, we aim to enhance the diversity of WGAN-generated data without compromising quality. Our results show that E-WGAN effectively increases the diversity of generated samples while preserving the stability and high quality of the outputs seen in standard WGANs. The proposed method offers promising results to further mitigating mode collapse and enhancing the generative capabilities of WGANs.

Spiking Neural Networks (SNNs) are increasingly explored for their energy efficiency and robustness in real-world applications, yet their privacy risks remain largely unexamined. In this work, we investigate the susceptibility of SNNs to Membership Inference Attacks (MIAs)-a major privacy threat where an adversary attempts to determine whether a given sample was part of the training dataset. While prior work suggests that SNNs may offer inherent robustness due to their discrete, event-driven nature, we find that its resilience diminishes as latency (T) increases. Furthermore, we introduce an input dropout strategy under black box setting, that significantly enhances membership inference in SNNs. Our findings challenge the assumption that SNNs are inherently more secure, and even though they are expected to be better, our results reveal that SNNs exhibit privacy vulnerabilities that are equally comparable to Artificial Neural Networks (ANNs).

Deep reinforcement learning (DRL) has shown remarkable success in tackling complex tasks by learning representations directly from raw data. However, as DRL agents become increasingly sophisticated, they often face challenges in adapting to new tasks or environments due to their monolithic structure. In this paper, we prove that by decomposing the agent into modular components, we enable more efficient adaptation as well as more efficient than that of the singular DRL agent on tackling complex tasks. Overall, our work contributes to advancing the field of DRL by introducing a flexible and scalable framework for agent decomposition. By enabling the creation of modular agents, we empower DRL systems to efficiently adapt to changing environments, learn new tasks with minimal intervention, and achieve higher levels of performance and versatility.

Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Weight decay is a standard technique to improve generalization performance in modern deep neural network optimization, and is also widely adopted in federated learning (FL) to prevent overfitting in local clients. In this paper, we first explore the choices of weight decay and identify that weight decay value appreciably influences the convergence of existing FL algorithms. While preventing overfitting is crucial, weight decay can introduce a different optimization goal towards the global objective, which is further amplified in FL due to multiple local updates and heterogeneous data distribution. To address this challenge, we develop {\it Federated optimization with Normalized Annealing Regularization} (FedNAR), a simple yet effective and versatile algorithmic plug-in that can be seamlessly integrated into any existing FL algorithms. Essentially, we regulate the magnitude of each update by performing co-clipping of the gradient and weight decay. We provide a comprehensive theoretical analysis of FedNAR's convergence rate and conduct extensive experiments on both vision and language datasets with different backbone federated optimization algorithms. Our experimental results consistently demonstrate that incorporating FedNAR into existing FL algorithms leads to accelerated convergence and heightened model accuracy. Moreover, FedNAR exhibits resilience in the face of various hyperparameter configurations. Specifically, FedNAR has the ability to self-adjust the weight decay when the initial specification is not optimal, while the accuracy of traditional FL algorithms would markedly decline. Our codes are released at \href{https://anonymous.4open.science/r/fednar-BE8F}{https://anonymous.4open.science/r/fednar-BE8F}.

This paper presents WiPose, the first 3D human pose construction framework using commercial WiFi devices. From the pervasive WiFi signals, WiPose can reconstruct 3D skeletons composed of the joints on both limbs and torso of the human body. By overcoming the technical challenges faced by traditional camera-based human perception solutions, such as lighting and occlusion, the proposed WiFi human sensing technique demonstrates the potential to enable a new generation of applications such as health care, assisted living, gaming, and virtual reality. WiPose is based on a novel deep learning model that addresses a series of technical challenges. First, WiPose can encode the prior knowledge of human skeleton into the posture construction process to ensure the estimated joints satisfy the skeletal structure of the human body. Second, to achieve cross environment generalization, WiPose takes as input a 3D velocity profile which can capture the movements of the whole 3D space, and thus separate posture-specific features from the static objects in the ambient environment. Finally, WiPose employs a recurrent neural network (RNN) and a smooth loss to enforce smooth movements of the generated skeletons. Our evaluation results on a real-world WiFi sensing testbed with distributed antennas show that WiPose can localize each joint on the human skeleton with an average error of 2.83cm, achieving a 35% improvement in accuracy over the state-of-the-art posture construction model designed for dedicated radar sensors.