Related papers: Mitigating the Backdoor Effect for Multi-Task Mode…

Task arithmetic is a straightforward yet highly effective strategy for model merging, enabling the resultant model to exhibit multi-task capabilities. Recent research indicates that models demonstrating linearity enhance the performance of…

Deep Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robustness problems and solved separately, since they belong to…

As an effective approach to equip models with multi-task capabilities without additional training, model merging has garnered significant attention. However, existing methods face challenges of redundant parameter conflicts and the…

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention…

The vulnerability of smartphones to cyberattacks has been a severe concern to users arising from the integrity of installed applications (\textit{apps}). Although applications are to provide legitimate and diversified on-the-go services,…

Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g.,…

The low detectability and low cost of unmanned aerial vehicles (UAVs) allow them to swarm near the radar network for effective jamming. The key to jamming is the reasonable task assignment and resource allocation of UAVs. However, the…

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage broad generalization. However, it remains unclear how…

The digital world is witnessing the rapid rise of LLM-based multi-agent systems (MASs) and their powerful applications. However, their security remains insufficiently understood, as existing evaluations are largely limited to narrow attack…

As collaborative learning and the outsourcing of data collection become more common, malicious actors (or agents) which attempt to manipulate the learning process face an additional obstacle as they compete with each other. In backdoor…

Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…

Model merging combines independently trained models into a single multi-task model. However, most existing approaches focus primarily on avoiding task interference. We argue that its greater potential lies in enabling task synergy, where…

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high…

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

As backdoor attacks become more stealthy and robust, they reveal critical weaknesses in current defense strategies: detection methods often rely on coarse-grained feature statistics, and purification methods typically require full…

Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the…

Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain…

Model merging, a method that combines the parameters and embeddings of multiple fine-tuned large language models (LLMs), offers a promising approach to enhance model performance across various tasks while maintaining computational…