Related papers: LoBAM: LoRA-Based Backdoor Attack on Model Merging
Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…
The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…
Parameter-efficient continual learning has emerged as a promising approach for large language models (LLMs) to mitigate catastrophic forgetting while enabling adaptation to new tasks. Current Low-Rank Adaptation (LoRA) continual learning…
Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…
Finetuning open-weight Large Language Models (LLMs) is standard practice for achieving task-specific performance improvements. Until now, finetuning has been regarded as a controlled and secure process in which training on benign datasets…
Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…
Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neglect of the model's…
AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…
Model merging, which combines multiple domain-specialized experts into a single model, offers a practical path to endow Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) with broad capabilities without the cost of…
In this study, we evaluate the effect of model merging in ad-hoc retrieval tasks. Model merging is a technique that combines the diverse characteristics of multiple models. We hypothesized that applying model merging to domain-specific…
Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of…
Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…
Fine-tuning is a crucial paradigm for adapting pre-trained large language models to downstream tasks. Recently, methods like Low-Rank Adaptation (LoRA) have been shown to effectively fine-tune LLMs with an extreme reduction in trainable…
Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…
Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…
The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption has fostered the…
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…
Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptible to backdoor…
For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…