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 chainof-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,

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 attacking scenarios, our attack amplification approach elevates the attack success rate (ASR) of existing backdoor attacks to nearly 100% while reducing training time by up to 20×.

Diffusion models (DMs) are state-of-the-art generative models that learn to model complex data distributions based on iterative noise addition and denoising. Thanks to their superior capacity in generative tasks, DMs have been investigated for various applications in the communication field such as network optimization, channel estimation, semantic communication, and cybersecurity. However, recent studies have shown their vulnerability regarding backdoor attacks, in which backdoored DMs consistently generate a designated harmful result 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. 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.

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.

Metaverse allows a 3D virtual mapping of the physical world to the digital world in which users interact with each other via digital avatars with a wide range of virtual activities. To realize this, the metaverse will inevitably employ numerous machine learning (ML) systems to enable the virtual-physical mapping process and offer intelligent virtual services to metaverse users (MUs). However, metaverse service providers (MSPs), who need ML models for their services (e.g., virtual events and healthcare services), may not have the expertise or resources required to build these underlying ML models. In addition, although ML models can be offered by a crowd of experienced ML workers (MLWs), the MLWs might not be able to collect the desired data for training their ML models due to privacy issues and the large-scale, distributed nature of the metaverse. In this paper, we propose MetaCrowd, a blockchain-based ML crowdsourcing framework that aims to overcome the mentioned issues and make ML accessible to a wide range of MUs and MSPs. Unlike traditional crowdsourcing systems which rely on central authorities, MetaCrowd is decentralized and automatic thanks to blockchain and smart contracts, thereby mitigating the single point of failure and trust issues. Experimental results illustrate the efficiency of MetaCrowd in both performance and cost. In addition, a decentralized application is also implemented and published widely to show its feasibility in practice.

Recent generative diffusion models are attracting enormous attention with various breakthroughs in text-to-image, text-guided image-to-image, and text-to-3D generation. In this paper, we propose MobileGen3D, a bridge between text-driven real-world-to-3D generation and real-time on-device rendering. Given several real-world images of a person/object and a text prompt, MobileGen3D can provide a 3D model of the given content which has been customized according to the text prompt and can be rendered on mobile devices in real-time. No additional 3D training data is required in our method. Based on neural light fields (NeLF), MobileGen3D speeds up the inference process dramatically compared to other 3D synthesis methods that rely on neural radiance fields (NeRF). As a result, we demonstrate that our method can generate high-resolution 3D contents with realistic edits and low disk storage requirement of just 6.48 MB. These 3D contents can be rendered directly by mobile devices and augmented/virtual reality devices with a high rendering speed of 61.2 FPS on our experimented iPhone 14. Our implementation is available with detailed guidelines at this page: https://github.com/tuanvu171/MobileGen3D

The emerging metaverse is envisioned as a virtual mapping of the real world, thus it would inevitably employ numerous Machine Learning (ML) frameworks to analyze and process massive data for the virtual-physical synchronization process. As a distributed ML paradigm, Federated Learning (FL) can naturally take advantage of numerous IoT, wearable devices, and edge, cloud servers under the metaverse infrastructure to train ML models with privacy guarantee. However, the large-scale and decentralized nature of the metaverse can pose significant challenges to traditional FL schemes, where there is a centralized server aggregating the local models received from local devices. It is not only vulnerable to Single Point of Failure (SPoF), but also lacks incentive mechanisms encouraging metaverse users to contribute their resources and data. In this paper, we propose BFLMeta, a blockchain-based FL scheme for the metaverse in which the aggregation process is performed in a decentralized manner, while the framework can estimate the non-IID degree of data to flexibly adjust blockchain committee size, thereby mitigating the impact of malicious aggregators. Security analysis shows that BFLMeta can resist SPoF, poisoning attack, privacy leakage, and sybil attack. Besides, our evaluation on computation, communication, and performance illustrates the efficiency of BFLMeta. Notably, BFLMeta can converge even with more than 50% poisoning nodes.

In the current age of digital world with the emergence of metaverse, digital assets are increasingly recognized and become more and more valuable. Unlike real-world assets, managing digital contents is more challenging since their associated information might be leaked widely on the Internet, making them worthless. Traditional digital asset management (DAM) systems based on third-party authorities and centralized databases have various weaknesses, threatening the benefits of stakeholders. In this paper, we propose a blockchain-based DAM framework utilizing smart contract, InterPlanetary File System (IPFS), and multi-layer encryption mechanisms for access control of digital assets in the metaverse. Our proposed design eliminates the intervention of intermediaries and offers a wide range of advanced security features such as resistance against data leakage and data alteration without trust assumptions among participants. Besides, key features of blockchain are leveraged to provide the system with immutability, traceability and transparency of information. To prove the feasibility of our design, we build a Decentralized Application (DApp) operating as a marketplace for digital assets using the proposed DAM framework. Experimental results indicate that the framework is more cost-effective than existing platforms, while advanced security features are integrated and automation is maximized.