Related papers: Architectural Backdoors for Within-Batch Data Stea…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with. A well-known vulnerability is a backdoor introduced into a…

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses…

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

Split learning is a collaborative learning design that allows several participants (clients) to train a shared model while keeping their datasets private. Recent studies demonstrate that collaborative learning models, specifically federated…

These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…

The democratization of pre-trained language models through open-source initiatives has rapidly advanced innovation and expanded access to cutting-edge technologies. However, this openness also brings significant security risks, including…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Diffusion models are state-of-the-art deep learning empowered generative models that are trained based on the principle of learning forward and reverse diffusion processes via progressive noise-addition and denoising. To gain a better…

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…

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approach to facilitate knowledge transfer among these…

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers…

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidden behaviors that activate under specific conditions.…

Backdoor attacks pose a significant threat to the integrity and reliability of Artificial Intelligence (AI) models, enabling adversaries to manipulate model behavior by injecting poisoned data with hidden triggers. These attacks can lead to…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…