Related papers: ALBERTA: ALgorithm-Based Error Resilience in Trans…

Remote Memory Access (RMA) is an emerging mechanism for programming high-performance computers and datacenters. However, little work exists on resilience schemes for RMA-based applications and systems. In this paper we analyze fault…

Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles. However, despite their superior…

The increasing prevalence of adversarial attacks on Artificial Intelligence (AI) systems has created a need for innovative security measures. However, the current methods of defending against these attacks often come with a high computing…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. However, the evolutionary laws of hierarchical representations, task knowledge formation…

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

The vulnerability of deep neural networks to adversarial examples has motivated an increasing number of defense strategies for promoting model robustness. However, the progress is usually hampered by insufficient robustness evaluations. As…

software component misuse a privileged relationship with the hardware to by pass system protections, monitors, or forensic tools. These relationships are often not illegal and exist between system components by design. Hence, even a system…

Pre-trained Transformers often exhibit over-confidence in source patterns and difficulty in forming new target-domain patterns during fine-tuning. We formalize the mechanism of output saturation leading to gradient suppression through…

As Large Language Models (LLMs) are increasingly deployed in mission-critical software systems, detecting hallucinations and ``faked truthfulness'' has become a paramount engineering challenge. Current reliability architectures rely heavily…

Autonomous vehicles (AVs) promise efficient, clean and cost-effective transportation systems, but their reliance on sensors, wireless communications, and decision-making systems makes them vulnerable to cyberattacks and physical threats.…

One of the most pressing challenges prevalent in the steel manufacturing industry is the identification of surface defects. Early identification of casting defects can help boost performance, including streamlining production processes.…

Transformers have revolutionized Computer Vision (CV) through self-attention mechanisms. However, their complexity makes latent token representations difficult to interpret. We introduce ULTra, a framework for interpreting Transformer…

Executing machine learning inference tasks on resource-constrained edge devices requires careful hardware-software co-design optimizations. Recent examples have shown how transformer-based deep neural network models such as ALBERT can be…

The rapid advancement of generative models has led to a growing prevalence of highly realistic AI-generated images, posing significant challenges for digital forensics and content authentication. Conventional detection methods mainly rely…

Large language models (LLMs) are highly compute- and memory-intensive, posing significant demands on high-performance GPUs. At the same time, advances in GPU technology driven by shrinking transistor sizes and lower operating voltages have…

Many ensemble-based models have been proposed to solve machine learning problems in the survival analysis framework, including random survival forests, the gradient boosting machine with weak survival models, ensembles of the Cox models. To…

A rising number of botnet families have been successfully detected using deep learning architectures. While the variety of attacks increases, these architectures should become more robust against attacks. They have been proven to be very…

Modern Transformer-based models frequently suffer from miscalibration, producing overconfident predictions that do not reflect true empirical frequencies. This work investigates the calibration dynamics of LoRA: Low-Rank Adaptation and a…

To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff…