Related papers: Scalable and Interpretable Verification of Image-b…

Variational Autoencoders (VAEs) provide a flexible and scalable framework for non-linear dimensionality reduction. However, in application domains such as genomics where data sets are typically tabular and high-dimensional, a black-box…

Security researchers grapple with the surge of malicious files, necessitating swift identification and classification of malware strains for effective protection. Visual classifiers and in particular Convolutional Neural Networks (CNNs)…

In Autonomous Driving (AD) transparency and safety are paramount, as mistakes are costly. However, neural networks used in AD systems are generally considered black boxes. As a countermeasure, we have methods of explainable AI (XAI), such…

Stacked Auto-Encoder (SAE) is a kind of deep learning algorithm for unsupervised learning. Which has multi layers that project the vector representation of input data into a lower vector space. These projection vectors are dense…

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Learning reliably safe autonomous control is one of the core problems in trustworthy autonomy. However, training a controller that can be formally verified to be safe remains a major challenge. We introduce a novel approach for learning…

Using synthesized images to boost the performance of perception models is a long-standing research challenge in computer vision. It becomes more eminent in visual-centric autonomous driving systems with multi-view cameras as some long-tail…

Conditional Variational Auto Encoders (VAE) are gathering significant attention as an Explainable Artificial Intelligence (XAI) tool. The codes in the latent space provide a theoretically sound way to produce counterfactuals, i.e.…

We propose VISION-SLS, a method for nonlinear output-feedback control from high-resolution RGB images which provides robust constraint satisfaction guarantees under calibrated uncertainty bounds despite partial observability, sensor noise,…

Explainable Artificial Intelligence (XAI) models have recently attracted a great deal of interest from a variety of application sectors. Despite significant developments in this area, there are still no standardized methods or approaches…

In the last decade, deep learning (DL) approaches have been used successfully in computer vision (CV) applications. However, DL-based CV models are generally considered to be black boxes due to their lack of interpretability. This black box…

Deep Neural Networks have become the dominant solution for Autonomous Driving perception, but their opacity conflicts with emerging Trustworthy AI guidelines and complicates safety assurance, debugging, and human oversight. While…

As AI systems migrate to safety-critical domains, verifying that their actions comply with well-defined rules remains a challenge. Formal methods provide provable guarantees but demand hand-crafted temporal-logic specifications, offering…

Autonomous vehicles bring the promise of enhancing the consumer experience in terms of comfort and convenience and, in particular, the safety of the autonomous vehicle. Safety functions in autonomous vehicles such as Automatic Emergency…

Deep Neural Networks (DNNs) have revolutionized various fields by enabling task automation and reducing human error. However, their internal workings and decision-making processes remain obscure due to their black box nature. Consequently,…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…

The security of autonomous vehicle networks is facing major challenges, owing to the complexity of sensor integration, real-time performance demands, and distributed communication protocols that expose vast attack surfaces around both…

A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…

Precise and comprehensive situational awareness is a critical capability of modern autonomous systems. Deep neural networks that perceive task-critical details from rich sensory signals have become ubiquitous; however, their black-box…