Related papers: ALBERTA: ALgorithm-Based Error Resilience in Trans…
Addressing the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios, this paper proposes a Transformer$^{-1}$ architecture based on the principle of deep adaptivity. This architecture achieves…
Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks remains poorly characterized, and whether model scale or inference mode affects robustness is…
Many aerospace and automotive applications use FPGAs in their designs due to their low power and reconfigurability requirements. Meanwhile, such applications also pose a high standard on system reliability, which makes the early-stage…
With the upcoming large-scale surveys like LSST, we expect to find approximately $10^5$ strong gravitational lenses among data of many orders of magnitude larger. In this scenario, the usage of non-automated techniques is too time-consuming…
The number of end devices that use the last mile wireless connectivity is dramatically increasing with the rise of smart infrastructures and require reliable functioning to support smooth and efficient business processes. To efficiently…
Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…
Bearing fault detection is a critical task in predictive maintenance, where accurate and timely fault identification can prevent costly downtime and equipment damage. Traditional attention mechanisms in Transformer neural networks often…
Embedded vision systems need efficient and robust image processing algorithms to perform real-time, with resource-constrained hardware. This research investigates image processing algorithms, specifically edge detection, corner detection,…
Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We present a novel dual-threshold conformalization framework…
Numerous real-world decisions rely on machine learning algorithms and require calibrated uncertainty estimates. However, modern methods often yield overconfident, uncalibrated predictions. The dominant approach to quantifying the…
Context: Software vulnerabilities pose significant security threats to software systems, especially as software is increasingly used across many areas of daily life, including health, government, and finance. Recently, transformer-based…
Deep optics has emerged as a promising approach by co-designing optical elements with deep learning algorithms. However, current research typically overlooks the analysis and optimization of manufacturing and assembly tolerances. This…
Modern machine learning (ML) has grown into a tightly coupled, full-stack ecosystem that combines hardware, software, network, and applications. Many users rely on cloud providers for elastic, isolated, and cost-efficient resources.…
AI-generated text is nowadays produced at scale across domains and heterogeneous generation pipelines, making robustness to distribution shift a central requirement for supervised binary detectors. We train transformer-based detectors on…
Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…
The Volterra Tensor Network lifts the curse of dimensionality for truncated, discrete times Volterra models, enabling scalable representation of highly nonlinear system. This scalability comes at the cost of introducing randomness through…
We develop a resilient binary hypothesis testing framework for decision making in adversarial multi-robot crowdsensing tasks. This framework exploits stochastic trust observations between robots to arrive at tractable, resilient decision…
The rise of hardware-level security threats, such as side-channel attacks, hardware Trojans, and firmware vulnerabilities, demands advanced detection mechanisms that are more intelligent and adaptive. Traditional methods often fall short in…
As software becomes increasingly complex and prone to vulnerabilities, automated vulnerability detection is critically important, yet challenging. Given the significant successes of large language models (LLMs) in various tasks, there is…
With the proliferation of various online and mobile payment systems, credit card fraud has emerged as a significant threat to financial security. This study focuses on innovative applications of the latest Transformer models for more robust…