相关论文: Attacking Attention of Foundation Models Disrupts …

We survey applications of pretrained foundation models in robotics. Traditional deep learning models in robotics are trained on small datasets tailored for specific tasks, which limits their adaptability across diverse applications. In…

Vision Transformers (ViTs) have outperformed traditional Convolutional Neural Networks (CNN) across various computer vision tasks. However, akin to CNN, ViTs are vulnerable to backdoor attacks, where the adversary embeds the backdoor into…

Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model…

With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered. One such vulnerability makes itpossible for an adversary to obtain private information about the types of…

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

Large-scale Video Foundation Models (VFMs) has significantly advanced various video-related tasks, either through task-specific models or Multi-modal Large Language Models (MLLMs). However, the open accessibility of VFMs also introduces…

Foundation models--such as GPT, CLIP, and DINO--have achieved revolutionary progress in the past several years and are commonly believed to be a promising approach for general-purpose AI. In particular, self-supervised learning is adopted…

Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…

Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary could tamper with a small number of model parameter bits to break the integrity of DNNs. To mitigate such threats, a batch of defense methods are…

Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns…

Although Deep Neural Networks (DNNs), such as the convolutional neural networks (CNN) and Vision Transformers (ViTs), have been successfully applied in the field of computer vision, they are demonstrated to be vulnerable to well-sought…

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a serious threat to security and safety critical systems. A…

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with…

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…

Understanding the mechanisms behind Vision Transformer (ViT), particularly its vulnerability to adversarial perturba tions, is crucial for addressing challenges in its real-world applications. Existing ViT adversarial attackers rely on la…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

Foundation models are pre-trained on massive data and transferred to downstream tasks via fine-tuning. This work presents Vision Middleware (ViM), a new learning paradigm that targets unified transferring from a single foundation model to a…