arXiv subjects

Long Bao Le

Publications and source records attributed to Long Bao Le.

At least 19 recordsLinked to original sources

arXiv2026

TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger

Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. However, existing backdoor methods face critical trade-offs among key factors: attack performance, stealthiness, time complexity, and required poison rates. For example, achieving high attack performance typically demands a high poison rate and prolonged training, which undermines stealthiness, making the attack more detectable by backdoor defenses. This paper proposes TooBad (trigger optimization for backdoor diffusion models), a backdoor framework which introduces a novel DM-tailored trigger optimization technique to dramatically enhance the performance of backdoor attacks on DMs. Experiments on representative benchmarks such as CIFAR-10 show that TooBad can achieve high ASRs ($> 85$%) at only 0.5% poison rate, significantly lower than the 10% typically required by prior work on the same datasets. At 5% poison rate, TooBad reaches nearly 100% ASR within just 3-5 backdoor injection epochs, whereas existing methods need at least 30-50 epochs at double the poison rate for comparable results. Despite its potency, TooBad easily evades SOTA defenses and maintains high utility. These results reveal a critical threat on DMs and highlight the need for more robust defenses against such stealthy yet efficient attacks.

cs.CR↗

arXiv2026

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models

Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes the model to generate a specific target word, choice, or class (depending on the task). Recent advances, however, exploit the long-form reasoning tendencies of modern LLMs to conduct reasoning-level backdoors: once triggered, the victim model inserts one or more malicious reasoning steps into its chain-of-thought (CoT). These attacks are substantially harder to detect, as the backdoored answer remains plausible and consistent with the poisoned reasoning trajectory. Yet, defenses tailored to this type of backdoor remain largely unexplored. To bridge this gap, we propose Critical-CoT, a novel defense mechanism that conducts a two-stage fine-tuning (FT) process on LLMs to develop critical thinking behaviors, enabling them to automatically identify potential backdoors and refuse to generate malicious reasoning steps. Extensive experiments across multiple LLMs and datasets demonstrate that Critical-CoT provides strong robustness against both in-context learning-based and FT-based backdoor attacks. Notably, Critical-CoT exhibits strong cross-domain and cross-task generalization. Our code is available at hthttps://github.com/tuanvu171/Critical-CoT.

cs.CR↗

arXiv2026

Agentic AI Meets Edge Computing in Autonomous UAV Swarms

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.

cs.RO↗

arXiv2025

A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models

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.

cs.CV↗

arXiv2024

Automatic Structured Pruning for Efficient Architecture in Federated Learning

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.

cs.CV↗

arXiv2024

PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models

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.

cs.AI↗

arXiv2024

Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey

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.

cs.CR↗

arXiv2024

Delay and Overhead Efficient Transmission Scheduling for Federated Learning in UAV Swarms

This paper studies the wireless scheduling design to coordinate the transmissions of (local) model parameters of federated learning (FL) for a swarm of unmanned aerial vehicles (UAVs). The overall goal of the proposed design is to realize the FL training and aggregation processes with a central aggregator exploiting the sensory data collected by the UAVs but it considers the multi-hop wireless network formed by the UAVs. Such transmissions of model parameters over the UAV-based wireless network potentially cause large transmission delays and overhead. Our proposed framework smartly aggregates local model parameters trained by the UAVs while efficiently transmitting the underlying parameters to the central aggregator in each FL global round. We theoretically show that the proposed scheme achieves minimal delay and communication overhead. Extensive numerical experiments demonstrate the superiority of the proposed scheme compared to other baselines.

eess.SP↗

arXiv2021

Intelligent Radio Signal Processing: A Survey

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.

eess.SP↗

arXiv2021

Federated Learning Meets Blockchain in Edge Computing: Opportunities and Challenges

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.

cs.CR↗

arXiv2020

Channel Estimation, Interference Cancellation, and Symbol Detection for Communications on Overlapping Channels

In this paper, we propose the joint interference cancellation, fast fading channel estimation, and data symbol detection for a general interference setting where the interfering source and the interfered receiver are unsynchronized and occupy overlapping channels of different bandwidths. The interference must be canceled before the channel estimation and data symbol detection of the desired communication are performed. To this end, we have to estimate the Effective Interference Coefficients (EICs) and then the desired fast fading channel coefficients. We construct a two-phase framework where the EICs and desired channel coefficients are estimated using the joint maximum likelihood-maximum a posteriori probability (JML-MAP) criteria in the first phase; and the MAP based data symbol detection is performed in the second phase. Based on this two-phase framework, we also propose an iterative algorithm for interference cancellation, channel estimation and data detection. We analyze the channel estimation error, residual interference, symbol error rate (SER) achieved by the proposed framework. We then discuss how to optimize the pilot density to achieve the maximum throughput. Via numerical studies, we show that our design can effectively mitigate the interference for a wide range of SNR values, our proposed channel estimation and symbol detection design can achieve better performances compared to the existing method. Moreover, we demonstrate the improved performance of the iterative algorithm with respect to the non-iterative counterpart.

eess.SP↗

arXiv2020

Joint Computation Offloading, SFC Placement, and Resource Allocation for Multi-Site MEC Systems

Network function Virtualization (NFV) and Mobile Edge Computing (MEC) are promising 5G technologies to support resource-demanding mobile applications. In NFV, one must process the service function chain (SFC) in which a set of network functions must be executed in a specific order. Moreover, the MEC technology enables computation offloading of service requests from mobile users to remote servers to potentially reduce energy consumption and processing delay for the mobile application. This paper considers the optimization of the computation offloading, resource allocation, and SFC placement in the multi-site MEC system. Our design objective is to minimize the weighted normalized energy consumption and computing cost subject to the maximum tolerable delay constraint. To solve the underlying mixed integer and non-linear optimization problem, we employ the decomposition approach where we iteratively optimize the computation offloading, SFC placement and computing resource allocation to obtain an efficient solution. Numerical results show the impacts of different parameters on the system performance and the superior performance of the proposed algorithm compared to benchmarking algorithms.

cs.DC↗

arXiv2020

A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art

Driven by the emergence of new compute-intensive applications and the vision of the Internet of Things (IoT), it is foreseen that the emerging 5G network will face an unprecedented increase in traffic volume and computation demands. However, end users mostly have limited storage capacities and finite processing capabilities, thus how to run compute-intensive applications on resource-constrained users has recently become a natural concern. Mobile edge computing (MEC), a key technology in the emerging fifth generation (5G) network, can optimize mobile resources by hosting compute-intensive applications, process large data before sending to the cloud, provide the cloud computing capabilities within the radio access network (RAN) in close proximity to mobile users, and offer context-aware services with the help of RAN information. Therefore, MEC enables a wide variety of applications, where the real-time response is strictly required, e.g., driverless vehicles, augmented reality, robotics, and immerse media. Indeed, the paradigm shift from 4G to 5G could become a reality with the advent of new technological concepts. The successful realization of MEC in the 5G network is still in its infancy and demands for constant efforts from both academic and industry communities. In this survey, we first provide a holistic overview of MEC technology and its potential use cases and applications. Then, we outline up-to-date researches on the integration of MEC with the new technologies that will be deployed in 5G and beyond. We also summarize testbeds and experimental evaluations, and open source activities, for edge computing. We further summarize lessons learned from state-of-the-art research works as well as discuss challenges and potential future directions for MEC research.

cs.NI↗

arXiv2019

Next-generation Wireless Solutions for the Smart Factory, Smart Vehicles, the Smart Grid and Smart Cities

5G wireless systems will extend mobile communication services beyond mobile telephony, mobile broadband, and massive machine-type communication into new application domains, namely the so-called vertical domains including the smart factory, smart vehicles, smart grid, smart city, etc. Supporting these vertical domains comes with demanding requirements: high-availability, high-reliability, low-latency, and in some cases, high-accuracy positioning. In this survey, we first identify the potential key performance requirements of 5G communication in support of automation in the vertical domains and highlight the 5G enabling technologies conceived for meeting these requirements. We then discuss the key challenges faced both by industry and academia which have to be addressed in order to support automation in the vertical domains. We also provide a survey of the related research dedicated to automation in the vertical domains. Finally, our vision of 6G wireless systems is discussed briefly.

eess.SP↗

arXiv2019

Joint Data compression and Computation offloading in Hierarchical Fog-Cloud Systems

Data compression has the potential to significantly improve the computation offloading performance in hierarchical fog-cloud systems. However, it remains unknown how to optimally determine the compression ratio jointly with the computation offloading decisions and the resource allocation. This joint optimization problem is studied in the current paper where we aim to minimize the maximum weighted energy and service delay cost (WEDC) of all users. First, we consider a scenario where data compression is performed only at the mobile users. We prove that the optimal offloading decisions have a threshold structure. Moreover, a novel three-step approach employing convexification techniques is developed to optimize the compression ratios and the resource allocation. Then, we address the more general design where data compression is performed at both the mobile users and the fog server. We propose three efficient algorithms to overcome the strong coupling between the offloading decisions and resource allocation. We show that the proposed optimal algorithm for data compression at only the mobile users can reduce the WEDC by a few hundred percent compared to computation offloading strategies that do not leverage data compression or use sub-optimal optimization approaches. Besides, the proposed algorithms for additional data compression at the fog server can further reduce the WEDC.

cs.IT↗

arXiv2019

Computation Offloading and Resource Allocation for Backhaul Limited Cooperative MEC Systems

In this paper, we jointly optimize computation offloading and resource allocation to minimize the weighted sum of energy consumption of all mobile users in a backhaul limited cooperative MEC system with multiple fog servers. Considering the partial offloading strategy and TDMA transmission at each base station, the underlying optimization problem with constraints on maximum task latency and limited computation resource at mobile users and fog servers is non-convex. We propose to convexify the problem exploiting the relationship among some optimization variables from which an optimal algorithm is proposed to solve the resulting problem. We then present numerical results to demonstrate the significant gains of our proposed design compared to conventional designs without exploiting cooperation among fog servers and a greedy algorithm.

cs.DC↗

arXiv2019

A Market-Based Framework for Multi-Resource Allocation in Fog Computing

Fog computing is transforming the network edge into an intelligent platform by bringing storage, computing, control, and networking functions closer to end-users, things, and sensors. How to allocate multiple resource types (e.g., CPU, memory, bandwidth) of capacity-limited heterogeneous fog nodes to competing services with diverse requirements and preferences in a fair and efficient manner is a challenging task. To this end, we propose a novel market-based resource allocation framework in which the services act as buyers and fog resources act as divisible goods in the market. The proposed framework aims to compute a market equilibrium (ME) solution at which every service obtains its favorite resource bundle under the budget constraint while the system achieves high resource utilization. This work extends the General Equilibrium literature by considering a practical case of satiated utility functions. Also, we introduce the notions of non-wastefulness and frugality for equilibrium selection, and rigorously demonstrate that all the non-wasteful and frugal ME are the optimal solutions to a convex program. Furthermore, the proposed equilibrium is shown to possess salient fairness properties including envy-freeness, sharing-incentive, and proportionality. Another major contribution of this work is to develop a privacy-preserving distributed algorithm, which is of independent interest, for computing an ME while allowing market participants to obfuscate their private information. Finally, extensive performance evaluation is conducted to verify our theoretical analyses.

cs.GT↗

arXiv2018

Joint Computation Offloading and Resource Allocation in Cloud Based Wireless HetNets

In this paper, we study the joint computation offloading and resource allocation problem in the two-tier wireless heterogeneous network (HetNet). Our design aims to optimize the computation offloading to the cloud jointly with the subchannel allocation to minimize the maximum (min-max) weighted energy consumption subject to practical constraints on bandwidth, computing resource and allowable latency for the multi-user multitask computation system. To tackle this non-convex mixed integer non-linear problem (MINLP), we employ the bisection search method to solve it where we propose a novel approach to transform and verify the feasibility of the underlying problem in each iteration. In addition, we propose a low-complexity algorithm, which can decrease the number of binary optimization variables and enable more scalable computation offloading optimization in the practical wireless HetNets. Numerical studies confirm that the proposed design achieves the energy saving gains about 55% in comparison with the local computation scheme under the strict required latency of 0.1s.

cs.NI↗