Related papers: LoBAM: LoRA-Based Backdoor Attack on Model Merging
Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static settings, this paper explores backdoor attacks in LVLM…
Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing trainable low-rank matrices. However, when integrated with…
Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While it assumes semantic equivalence between the original and compiled graphs, we first…
Low-Rank Adaptation (LoRA) is a parameter-efficient technique for rapidly fine-tuning foundation models. In standard LoRA training dynamics, models tend to quickly converge to a local optimum near the initialization. However, this local…
Fine-tuning large language models (LLMs) is a common practice to adapt generalist models to specialized domains. However, recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical…
Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…
Low-Rank Adaptation (LoRA), which leverages the insight that model updates typically reside in a low-dimensional space, has significantly improved the training efficiency of Large Language Models (LLMs) by updating neural network layers…
Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior…
Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of expert models and adapters, often shared via platforms like…
Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…
One key challenge in backdoor attacks against large foundation models is the resource limits. Backdoor attacks usually require retraining the target model, which is impractical for very large foundation models. Existing backdoor attacks are…
In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances…
The Large Language Models (LLMs) are poised to offer efficient and intelligent services for future mobile communication networks, owing to their exceptional capabilities in language comprehension and generation. However, the extremely high…
Model merging combines multiple models into a single model with aggregated capabilities, making it a powerful tool for large language model (LLM) development. However, scaling model merging is challenging: performance depends on the choice…
Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This…
Federated learning (FL) is a decentralized machine learning technique that allows multiple entities to jointly train a model while preserving dataset privacy. However, its distributed nature has raised various security concerns, which have…
Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to…
Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…
Developers increasingly construct multimodal large language models (MLLMs) by assembling pretrained components,introducing supply-chain attack surfaces.Existing security research primarily focuses on poisoning backbones such as encoders or…