Long Bao Le

Vu Tuan Truong, Luan Ba Dang, Long Bao Le

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they potentially are. Recent studies have shown that DMs are prone to a wide range of attacks, including adversarial attacks, membership inference, backdoor injection, and various multi-modal threats. Since numerous pre-trained DMs are published widely on the Internet, potential threats from these attacks are especially detrimental to the society, making DM-related security a worth investigating topic. Therefore, in this paper, we conduct a comprehensive survey on the security aspect of DMs, focusing on various attack and defense methods for DMs. First, we present crucial knowledge of DMs with five main types of DMs, including denoising diffusion probabilistic models, denoising diffusion implicit models, noise conditioned score networks, stochastic differential equations, and multi-modal conditional DMs. We further survey a variety of recent studies investigating different types of attacks that exploit the vulnerabilities of DMs. Then, we thoroughly review potential countermeasures to mitigate each of the presented threats. Finally, we discuss open challenges of DM-related security and envision certain research directions for this topic.

Junyao Shi, Rujia Yang, Kaitian Chao et al.

Today's best-explored routes towards generalist robots center on collecting ever larger "observations-in actions-out" robotics datasets to train large end-to-end models, copying a recipe that has worked for vision-language models (VLMs). We pursue a road less traveled: building generalist policies directly around VLMs by augmenting their general capabilities with specific robot capabilities encapsulated in a carefully curated set of perception, planning, and control modules. In Maestro, a VLM coding agent dynamically composes these modules into a programmatic policy for the current task and scenario. Maestro's architecture benefits from a streamlined closed-loop interface without many manually imposed structural constraints, and a comprehensive and diverse tool repertoire. As a result, it largely surpasses today's VLA models for zero-shot performance on challenging manipulation skills. Further, Maestro is easily extensible to incorporate new modules, easily editable to suit new embodiments such as a quadruped-mounted arm, and even easily adapts from minimal real-world experiences through local code edits.

Long Le, Yao Li

The firing dynamics of biological neurons in mathematical models is often determined by the model's parameters, representing the neurons' underlying properties. The parameter estimation problem seeks to recover those parameters of a single neuron or a neuron population from their responses to external stimuli and interactions between themselves. Most common methods for tackling this problem in the literature use some mechanistic models in conjunction with either a simulation-based or solution-based optimization scheme. In this paper, we study an automatic approach of learning the parameters of neuron populations from a training set consisting of pairs of spiking series and parameter labels via supervised learning. Unlike previous work, this automatic learning does not require additional simulations at inference time nor expert knowledge in deriving an analytical solution or in constructing some approximate models. We simulate many neuronal populations with different parameter settings using a stochastic neuron model. Using that data, we train a variety of supervised machine learning models, including convolutional and deep neural networks, random forest, and support vector regression. We then compare their performance against classical approaches including a genetic search, Bayesian sequential estimation, and a random walk approximate model. The supervised models almost always outperform the classical methods in parameter estimation and spike reconstruction errors, and computation expense. Convolutional neural network, in particular, is the best among all models across all metrics. The supervised models can also generalize to out-of-distribution data to a certain extent.

Vu Tuan Truong, Long Bao Le

Diffusion models (DMs) are advanced deep learning models that achieved state-of-the-art capability on a wide range of generative tasks. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored DMs consistently generate a designated result (e.g., a harmful image) called backdoor target when the models' input contains a backdoor trigger. Although various backdoor techniques have been investigated to attack DMs, defense methods against these threats are still limited and underexplored, especially in inverting the backdoor trigger. In this paper, we introduce PureDiffusion, a novel backdoor defense framework that can efficiently detect backdoor attacks by inverting backdoor triggers embedded in DMs. Our extensive experiments on various trigger-target pairs show that PureDiffusion outperforms existing defense methods with a large gap in terms of fidelity (i.e., how much the inverted trigger resembles the original trigger) and backdoor success rate (i.e., the rate that the inverted trigger leads to the corresponding backdoor target). Notably, in certain cases, backdoor triggers inverted by PureDiffusion even achieve higher attack success rate than the original triggers.

Mihir Parmar, Xin Liu, Palash Goyal et al.

Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification without considering constraints or apply inference-time algorithms without adapting to instance-level complexity. To address these limitations, we propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents. Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms--Best of N, Tree-of-Thought, and REBASE. In PlanGEN framework, the selection agent optimizes algorithm choice based on instance complexity, ensuring better adaptability to complex planning problems. Experimental results demonstrate significant improvements over the strongest baseline across multiple benchmarks, achieving state-of-the-art results on NATURAL PLAN ($\sim$8%$\uparrow$), OlympiadBench ($\sim$4%$\uparrow$), DocFinQA ($\sim$7%$\uparrow$), and GPQA ($\sim$1%$\uparrow$). Our key finding highlights that constraint-guided iterative verification improves inference-time algorithms, and adaptive selection further boosts performance on complex planning and reasoning problems.

Vu Tuan Truong, Long Bao Le

Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models generate specific, undesirable outputs called backdoor target (e.g., harmful images) when a pre-defined trigger is embedded to their inputs. In this paper, we propose PureDiffusion, a dual-purpose framework that simultaneously serves two contrasting roles: backdoor defense and backdoor attack amplification. For defense, we introduce two novel loss functions to invert backdoor triggers embedded in diffusion models. The first leverages trigger-induced distribution shifts across multiple timesteps of the diffusion process, while the second exploits the denoising consistency effect when a backdoor is activated. Once an accurate trigger inversion is achieved, we develop a backdoor detection method that analyzes both the inverted trigger and the generated backdoor targets to identify backdoor attacks. In terms of attack amplification with the role of an attacker, we describe how our trigger inversion algorithm can be used to reinforce the original trigger embedded in the backdoored diffusion model. This significantly boosts attack performance while reducing the required backdoor training time. Experimental results demonstrate that PureDiffusion achieves near-perfect detection accuracy, outperforming existing defenses by a large margin, particularly against complex trigger patterns. Additionally, in an attack scenario, our attack amplification approach elevates the attack success rate (ASR) of existing backdoor attacks to nearly 100\% while reducing training time by up to 20x.

Long Le, Marcel Hussing, Eric Eaton

This work studies the intersection of continual and federated learning, in which independent agents face unique tasks in their environments and incrementally develop and share knowledge. We introduce a mathematical framework capturing the essential aspects of distributed continual learning, including agent model and statistical heterogeneity, continual distribution shift, network topology, and communication constraints. Operating on the thesis that distributed continual learning enhances individual agent performance over single-agent learning, we identify three modes of information exchange: data instances, full model parameters, and modular (partial) model parameters. We develop algorithms for each sharing mode and conduct extensive empirical investigations across various datasets, topology structures, and communication limits. Our findings reveal three key insights: sharing parameters is more efficient than sharing data as tasks become more complex; modular parameter sharing yields the best performance while minimizing communication costs; and combining sharing modes can cumulatively improve performance.

Thuan Minh Nguyen, Vu Tuan Truong, Long Bao Le

The integration of agentic AI, powered by large language models (LLMs) with autonomous reasoning, planning, and execution, into unmanned aerial vehicle (UAV) swarms opens new operational possibilities and brings the vision of the Internet of Drones closer to reality. However, infrastructure constraints, dynamic environments, and the computational demands of multi-agent coordination limit real-world deployment in high-risk scenarios such as wildfires and disaster response. This paper investigates the integration of LLM-based agentic AI and edge computing to realize scalable and resilient autonomy in UAV swarms. We first discuss three architectures for supporting UAV swarms - standalone, edge-enabled, and edge-cloud hybrid deployment - each optimized for varying autonomy and connectivity levels. Then, a use case for wildfire search and rescue (SAR) is designed to demonstrate the efficiency of the edge-enabled architecture, enabling high SAR coverage, reduced mission completion times, and a higher level of autonomy compared to traditional approaches. Finally, we highlight open challenges in integrating LLMs and edge computing for mission-critical UAV-swarm applications.

Thai Vu Nguyen, Long Bao Le, Anderson Avila

In Federated Learning (FL), training is conducted on client devices, typically with limited computational resources and storage capacity. To address these constraints, we propose an automatic pruning scheme tailored for FL systems. Our solution improves computation efficiency on client devices, while minimizing communication costs. One of the challenges of tuning pruning hyper-parameters in FL systems is the restricted access to local data. Thus, we introduce an automatic pruning paradigm that dynamically determines pruning boundaries. Additionally, we utilized a structured pruning algorithm optimized for mobile devices that lack hardware support for sparse computations. Experimental results demonstrate the effectiveness of our approach, achieving accuracy comparable to existing methods. Our method notably reduces the number of parameters by 89% and FLOPS by 90%, with minimal impact on the accuracy of the FEMNIST and CelebFaces datasets. Furthermore, our pruning method decreases communication overhead by up to 5x and halves inference time when deployed on Android devices.

Dinh C. Nguyen, Ming Ding, Quoc-Viet Pham et al.

Mobile edge computing (MEC) has been envisioned as a promising paradigm to handle the massive volume of data generated from ubiquitous mobile devices for enabling intelligent services with the help of artificial intelligence (AI). Traditionally, AI techniques often require centralized data collection and training in a single entity, e.g., an MEC server, which is now becoming a weak point due to data privacy concerns and high data communication overheads. In this context, federated learning (FL) has been proposed to provide collaborative data training solutions, by coordinating multiple mobile devices to train a shared AI model without exposing their data, which enjoys considerable privacy enhancement. To improve the security and scalability of FL implementation, blockchain as a ledger technology is attractive for realizing decentralized FL training without the need for any central server. Particularly, the integration of FL and blockchain leads to a new paradigm, called FLchain, which potentially transforms intelligent MEC networks into decentralized, secure, and privacy-enhancing systems. This article presents an overview of the fundamental concepts and explores the opportunities of FLchain in MEC networks. We identify several main topics in FLchain design, including communication cost, resource allocation, incentive mechanism, security and privacy protection. The key solutions for FLchain design are provided, and the lessons learned as well as the outlooks are also discussed. Then, we investigate the applications of FLchain in popular MEC domains, such as edge data sharing, edge content caching and edge crowdsensing. Finally, important research challenges and future directions are also highlighted.

Quoc-Viet Pham, Nhan Thanh Nguyen, Thien Huynh-The et al.

Intelligent signal processing for wireless communications is a vital task in modern wireless systems, but it faces new challenges because of network heterogeneity, diverse service requirements, a massive number of connections, and various radio characteristics. Owing to recent advancements in big data and computing technologies, artificial intelligence (AI) has become a useful tool for radio signal processing and has enabled the realization of intelligent radio signal processing. This survey covers four intelligent signal processing topics for the wireless physical layer, including modulation classification, signal detection, beamforming, and channel estimation. In particular, each theme is presented in a dedicated section, starting with the most fundamental principles, followed by a review of up-to-date studies and a summary. To provide the necessary background, we first present a brief overview of AI techniques such as machine learning, deep learning, and federated learning. Finally, we highlight a number of research challenges and future directions in the area of intelligent radio signal processing. We expect this survey to be a good source of information for anyone interested in intelligent radio signal processing, and the perspectives we provide therein will stimulate many more novel ideas and contributions in the future.

Le Thanh Tan, Long Bao Le

In this paper, we consider the joint design of data compression and 802.15.4-based medium access control (MAC) protocol for smartgrids with renewable energy. We study the setting where a number of nodes, each of which comprises electricity load and/or renewable sources, report periodically their injected powers to a data concentrator. Our design exploits the correlation of the reported data in both time and space to efficiently design the data compression using the compressed sensing (CS) technique and theMAC protocol so that the reported data can be recovered reliably within minimum reporting time. Specifically, we perform the following design tasks: i) we employ the two-dimensional (2D) CS technique to compress the reported data in the distributed manner; ii) we propose to adapt the 802.15.4 MAC protocol frame structure to enable efficient data transmission and reliable data reconstruction; and iii) we develop an analytical model based on which we can obtain efficient MAC parameter configuration to minimize the reporting delay. Finally, numerical results are presented to demonstrate the effectiveness of our proposed framework compared to existing solutions.