相关论文: MoGU V2: Toward a Higher Pareto Frontier Between M…

Fine-tuning pretrained LLMs has been shown to be an effective strategy for reaching state-of-the-art performance on specific tasks like machine translation. However, this process of adaptation often implies sacrificing general-purpose…

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Large Language Models (LLMs) demonstrate strong potential across a variety of tasks in communications and networking due to their advanced reasoning capabilities. However, because different LLMs have different model structures and are…

Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns due to sensitive data transmission and require substantial communication bandwidth, which is…

The AI era has ushered in Large Language Models (LLM) to the technological forefront, which has been much of the talk in 2023, and is likely to remain as such for many years to come. LLMs are the AI models that are the power house behind…

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Large Vision-Language Models (LVLMs) have shown remarkable potential across a wide array of vision-language tasks, leading to their adoption in critical domains such as finance and healthcare. However, their growing deployment also…

Deploying and fine-tuning Large Language Models (LLMs) on resource-constrained edge devices requires navigating a strict trade-off between memory footprint and task performance. While Quantization-Aware Fine-tuning has emerged as a viable…

The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which…

With the extensive deployment of Large Language Models (LLMs), ensuring their safety has become increasingly critical. However, existing defense methods often struggle with two key issues: (i) inadequate defense capabilities, particularly…

Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We introduce LLMSecGuard, a framework to offer enhanced code…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers. The next frontier is LLM personalization, where a foundation model can be fine-tuned with user/task-specific data. Given the sensitive nature of…

Retrieval-Augmented Generation (RAG) has been shown to enhance the factual accuracy of Large Language Models (LLMs), but existing methods often suffer from limited reasoning capabilities in effectively using the retrieved evidence,…

Mixture-of-Experts (MoE) architectures have advanced the scaling of Large Language Models (LLMs) by activating only a sparse subset of parameters per input, enabling state-of-the-art performance with reduced computational cost. As these…

As the ubiquity and complexity of system-on-chip (SoC) designs increase across electronic devices, the task of incorporating security into an SoC design flow poses significant challenges. Existing security solutions are inadequate to…

Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achieve strong performance, their computational cost is…

Deploying large language models (LLMs) in edge-cloud environments requires an efficient routing strategy to balance cost and response quality. Traditional approaches prioritize either human-preference data or accuracy metrics from benchmark…

The rapid development and deployment of large language models (LLMs) have introduced a new frontier in artificial intelligence, marked by unprecedented capabilities in natural language understanding and generation. However, the increasing…

In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks: harmful images paired with low-resource language texts can easily bypass defenses designed for…