Related papers: LoBAM: LoRA-Based Backdoor Attack on Model Merging
Federated learning is a promising approach for training machine learning models while preserving data privacy. However, its distributed nature makes it vulnerable to backdoor attacks, particularly in NLP tasks, where related research…
Recent work has demonstrated robust mechanisms by which attacks can be orchestrated on machine learning models. In contrast to adversarial examples, backdoor or trojan attacks embed surgically modified samples with targeted labels in the…
Machine Learning using neural networks has received prominent attention recently because of its success in solving a wide variety of computational tasks, in particular in the field of computer vision. However, several works have drawn…
Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstream tasks typically involves adapting their knowledge…
Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing such information can have devastating consequences. Deep…
With the emerging trend in generative models and convenient public access to diffusion models pre-trained on large datasets, users can fine-tune these models to generate images of personal faces or items in new contexts described by natural…
The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…
Deep learning models are widely deployed in many applications, such as object detection in various security fields. However, these models are vulnerable to backdoor attacks. Most backdoor attacks were intensively studied on classified…
LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them vulnerable to backdoor attacks. Current…
With the prosperity of large language models (LLMs), powerful LLM-based intelligent agents have been developed to provide customized services with a set of user-defined tools. State-of-the-art methods for constructing LLM agents adopt…
Low-rank adaptations (LoRA) are widely used to fine-tune large models across various domains for specific downstream tasks. While task-specific LoRAs are often available, concerns about data privacy and intellectual property can restrict…
Recent large reasoning models (LRMs) have made substantial progress in complex reasoning tasks, yet they often generate lengthy reasoning paths for every query, incurring unnecessary computation and latency. Existing speed-up approaches…
Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in large pretrained model development due to its ability to…
Back-door attack poses a severe threat to deep learning systems. It injects hidden malicious behaviors to a model such that any input stamped with a special pattern can trigger such behaviors. Detecting back-door is hence of pressing need.…
Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats,…
Recent studies have shown that cooperative multi-agent deep reinforcement learning (c-MADRL) is under the threat of backdoor attacks. Once a backdoor trigger is observed, it will perform malicious actions leading to failures or malicious…
Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…
Parameter efficient finetuning (PEFT) methods are widely used in LLMs and generative models in computer vision. Especially one can use multiple of these during inference to change the behavior of the base model. In this paper we…
While convolutional neural networks (CNNs) have achieved success in computer vision tasks, it is vulnerable to backdoor attacks. Such attacks could mislead the victim model to make attacker-chosen prediction with a specific trigger pattern.…
While large language models (LLMs) such as Llama-2 or GPT-4 have shown impressive zero-shot performance, fine-tuning is still necessary to enhance their performance for customized datasets, domain-specific tasks, or other private needs.…