Large Language Models (LLMs), with remarkable conversational capabilities, have emerged as AI assistants that can handle both visual and textual modalities. However, their effectiveness in joint video-language understanding has not been extensively explored. In the article, we introduce Valley , a multi-modal foundation model designed to enable enhanced video comprehension and instruction-following capabilities. To this end, we construct two datasets, namely “ Valley-702k ” and “ Valley-instruct-73k ,” to cover a diverse range of video–text alignment and video-based instruction tasks, such as multi-shot captions, long video descriptions, action recognition, causal inference, and so on. Then, we adopt ViT-L/14 as the vision encoder and explore three different temporal modeling modules to learn multifaceted features for enhanced video understanding. In addition, we implement a two-phase training approach for Valley: the first phase focuses solely on training the projection module to facilitate the LLM’s capacity to understand visual input, and the second phase jointly trains the projection module and the LLM to improve their instruction following ability. Extensive experiments demonstrate that Valley has the potential to serve as an effective video assistant, simplifying complex video understanding tasks. Our code and data are publicly available at https://github.com/RupertLuo/Valley .

Federated Learning (FL) has emerged as a privacy-preserving distributed machine learning paradigm. To motivate data owners to contribute towards FL, research on FL incentive mechanisms is gaining great interest. Existing monetary incentive mechanisms generally share the same FL model with all participants regardless of their contributions. Such an assumption can be unfair towards participants who contributed more and promote undesirable free-riding, especially when the final model is of great utility value to participants. In this paper, we propose a Fairness-Aware Incentive Mechanism for federated learning (FedFAIM) to address such problem. It satisfies two types of fairness notion: 1) aggregation fairness, which determines aggregation results according to data quality; 2) reward fairness, which assigns each participant a unique model with performance reflecting his contribution. Aggregation fairness is achieved through efficient gradient aggregation which examines local gradient quality and aggregates them based on data quality. Reward fairness is achieved through an efficient Shapley value-based contribution assessment method and a novel reward allocation method based on reputation and distribution of local and global gradients. We further prove reward fairness is theoretically guaranteed. Extensive experiments show that FedFAIM provides stronger incentives than similar non-monetary FL incentive mechanisms while achieving a high level of fairness.

In federated learning (FL), malicious clients could manipulate the predictions of the trained model through backdoor attacks, posing a significant threat to the security of FL systems. Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A recent study conducted by Qin et al. [ 24 ] marks the initial exploration of backdoor attacks within the personalized federated learning (pFL) scenario, where each client constructs a personalized model based on its local data. Notably, the study demonstrates that pFL methods with parameter decoupling can significantly enhance robustness against backdoor attacks. However, in this article, we whistleblow that pFL methods with parameter decoupling are still vulnerable to backdoor attacks. The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts. We analyze two direct causes of the heterogeneous classifiers: (1) data heterogeneity inherently exists among clients and (2) poisoning by malicious clients further exacerbates the data heterogeneity. To address these issues, we propose a two-pronged attack method, BapFL, which comprises two simple yet effective strategies: (1) poisoning only the feature encoder while keeping the classifier fixed and (2) diversifying the classifier through noise introduction to simulate that of the benign clients. Extensive experiments on three benchmark datasets under varying conditions demonstrate the effectiveness of our proposed attack. Additionally, we evaluate the effectiveness of six widely used defense methods and find that BapFL still poses a significant threat even in the presence of the best defense, Multi-Krum. We hope to inspire further research on attack and defense strategies in pFL scenarios. The code is available at: https://github.com/BapFL/code

Training deep learning models collaboratively on decentralized edge devices has attracted significant attention recently. The two most prominent schemes for this problem are Federated Learning (FL) and Split Learning (SL). Although there have been several surveys and experimental evaluations for FL in the literature, SL paradigms have not yet been systematically reviewed and evaluated. Due to the diversity of SL paradigms in terms of label sharing, model aggregation, cut layer selection, etc., the lack of a systematic survey makes it difficult to fairly and conveniently compare the performance of different SL paradigms. To address the above issue, in this paper, we first provide a comprehensive review for existing SL paradigms. Then, we implement several typical SL paradigms and perform extensive experiments to compare their performance in different scenarios on four widely used datasets. The experimental results provide extensive engineering advice and research insights for SL paradigms. We hope that our work can facilitate future research on SL by establishing a fair and accessible benchmark for SL performance evaluation.

Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i.e., server and clients only hold partial sub-networks and exchange intermediate computations). However, existing research has mainly focused on examining its reliability for privacy protection, with little investigation into model security. Specifically, by exploring full models, attackers can launch adversarial attacks, and split learning can mitigate this severe threat by only disclosing part of models to untrusted servers. This paper aims to evaluate the robustness of split learning against adversarial attacks, particularly in the most challenging setting where untrusted servers only have access to the intermediate layers of the model. Existing adversarial attacks mostly focus on the centralized setting instead of the collaborative setting, thus, to better evaluate the robustness of split learning, we develop a tailored attack called SLADV, which comprises two stages: 1) shadow model training that addresses the issue of lacking part of the model and 2) local adversarial attack that produces adversarial examples to evaluate. The first stage only requires a few unlabeled non-IID data, and, in the second stage, SLADV perturbs the intermediate output of natural samples to craft the adversarial ones. The overall cost of the proposed attack process is relatively low, yet the empirical attack effectiveness is significantly high, demonstrating the surprising vulnerability of split learning to adversarial attacks.