相关论文: Gradient-Based Model Fingerprinting for LLM Simila…

Large Language Models (LLMs) have demonstrated strong capabilities in various natural language processing tasks; however, their application to graph-related problems remains limited, primarily due to scalability constraints and the absence…

The wide applicability and adaptability of generative large language models (LLMs) has enabled their rapid adoption. While the pre-trained models can perform many tasks, such models are often fine-tuned to improve their performance on…

Large language models (LLMs) have transformed human writing by enhancing grammar correction, content expansion, and stylistic refinement. However, their widespread use raises concerns about authorship, originality, and ethics, even…

The widespread deployment of large language models (LLMs) has intensified concerns around intellectual property (IP) protection, as model theft and unauthorized redistribution become increasingly feasible. To address this, model…

Instruction tuning is one of the key steps required for adapting large language models (LLMs) to a broad spectrum of downstream applications. However, this procedure is difficult because real-world datasets are rarely homogeneous; they…

Pre-training data detection for LLMs is essential for addressing copyright concerns and mitigating benchmark contamination. Existing methods mainly focus on the likelihood-based statistical features or heuristic signals before and after…

Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering operations such as fine-tuning (including PPO/DPO),…

Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely on clustering, which requires sufficient data and can fail…

The emergence of the Large Language Model (LLM) has shown their superiority in a wide range of disciplines, including language understanding and translation, relational logic reasoning, and even partial differential equations solving. The…

The public accessibility of large vision-language models (LVLMs) raises serious concerns about unauthorized model reuse and intellectual property infringement. Existing ownership verification methods often rely on semantically abnormal…

The rise of large language models (LLMs) like ChatGPT has significantly improved automated code generation, enhancing software development efficiency. However, this introduces challenges in academia, particularly in distinguishing between…

Protecting the intellectual property of large language models requires robust ownership verification. Conventional backdoor fingerprinting, however, is flawed by a stealth-robustness paradox: to be robust, these methods force models to…

Protecting the copyright of large language models (LLMs) has become crucial due to their resource-intensive training and accompanying carefully designed licenses. However, identifying the original base model of an LLM is challenging due to…

With the widespread application of Large Language Models (LLMs), their associated security issues have become increasingly prominent, severely constraining their trustworthy deployment in critical domains. This paper proposes a novel safety…

Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backdoor and poisoning attacks that induce the generation of…

Protecting the intellectual property of Large Language Models (LLMs) has become increasingly critical due to the high cost of training. Model merging, which integrates multiple expert models into a single multi-task model, introduces a…

Federated Learning (FL) is increasingly adopted as a decentralized machine learning paradigm due to its capability to preserve data privacy by training models without centralizing user data. However, FL is susceptible to indirect privacy…

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the…

Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and question answering. Due to their efficiency and versatility,…

Training large language models (LLMs) at the network edge faces fundamental challenges arising from device resource constraints, severe data heterogeneity, and heightened privacy risks. To address these challenges, we propose ELSA…