Related papers: T-MLA: A targeted multiscale log-exponential attac…
Multimodal Machine Learning systems, particularly those aligning text and image data like CLIP/BLIP models, have become increasingly prevalent, yet remain susceptible to adversarial attacks. While substantial research has addressed…
Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are…
Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image…
Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…
We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models. Our hypothesis is that perturbations produced in the wavelet space disrupt early…
Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…
Recently in robotics, Vision-Language-Action (VLA) models have emerged as a transformative approach, enabling robots to execute complex tasks by integrating visual and linguistic inputs within an end-to-end learning framework. Despite their…
Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI. However, the significant computational overhead of processing redundant visual tokens remains a critical bottleneck for real-time robotic deployment.…
With the rapid expansion of data lakes storing health data and hosting AI algorithms, a prominent concern arises: how safe is it to export machine learning models from these data lakes? In particular, deep network models, widely used for…
Deploying machine learning (ML) in dynamic data-driven applications systems (DDDAS) can improve the security of industrial control systems (ICS). However, ML-based DDDAS are vulnerable to adversarial attacks because adversaries can alter…
Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial…
We propose Neural Image Compression (NIC), a two-step method to build convolutional neural networks for gigapixel image analysis solely using weak image-level labels. First, gigapixel images are compressed using a neural network trained in…
The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly…
Model compression is crucial for minimizing memory storage and accelerating inference in deep learning (DL) models, including recent foundation models like large language models (LLMs). Users can access different compressed model versions…
Non-intrusive Load Monitoring (NILM) algorithms, commonly referred to as load disaggregation algorithms, are fundamental tools for effective energy management. Despite the success of deep models in load disaggregation, they face various…
The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…
With Vision-Language Pre-training (VLP) models demonstrating powerful multimodal interaction capabilities, the application scenarios of neural networks are no longer confined to unimodal domains but have expanded to more complex multimodal…
Recent advances in Large Visual Language Models (LVLMs) have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security…
Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired target class. Existing methods face two key limitations: (1)…