相关论文: Aggressive Compression Enables LLM Weight Theft

As Large Language Models (LLMs) continue to grow in size, storing and transmitting them on edge devices becomes increasingly challenging. Traditional methods like quantization and pruning struggle to achieve extreme compression of LLMs…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory…

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated…

Large language models (LLMs) have significantly influenced various industries but suffer from a critical flaw, the potential sensitivity of generating harmful content, which poses severe societal risks. We developed and tested novel attack…

Suffix-based jailbreak attacks append an adversarial suffix, i.e., a short token sequence, to steer aligned LLMs into unsafe outputs. Since suffixes are free-form text, they admit endlessly many surface forms, making jailbreak mitigation…

Distributed machine learning has been widely used in recent years to tackle the large and complex dataset problem. Therewith, the security of distributed learning has also drawn increasing attentions from both academia and industry. In this…

In recent years, compression of large language models (LLMs) has emerged as an important problem to enable language model deployment on resource-constrained devices, reduce computational costs, and mitigate the environmental footprint of…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of different types of…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study…

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates that model information can be leveraged to assist other…

Large Language Models are fundamental actors in the modern IT landscape dominated by AI solutions. However, security threats associated with them might prevent their reliable adoption in critical application scenarios such as government…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Recent advances in Large Language Models (LLMs) have led to impressive alignment where models learn to distinguish harmful from harmless queries through supervised finetuning (SFT) and reinforcement learning from human feedback (RLHF). In…

A novel hack involving Large Language Models (LLMs) has emerged, exploiting adversarial suffixes to deceive models into generating perilous responses. Such jailbreaks can trick LLMs into providing intricate instructions to a malicious user…

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…