Related papers: FT-Pilot: Automated Fault-Tolerant RTL Rewriting v…

Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural…

Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…

This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity approaches are often heavy or slow for modern LLMs. LM-Fix runs a short test-vector pass and…

The massive scale of modern AI accelerators presents critical challenges to traditional fault assessment methodologies, which face prohibitive computational costs and provide poor coverage of critical failure modes. This paper introduces…

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

In this paper, a fault-tolerant approach to mitigate transient and permanent faults of arithmetic and logic operations of embedded processors called FT-EALU is proposed. In this method, each operation is replicated in time and the derived…

Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve reliability at the system level or address specific issues…

Convolutional Neural Networks (CNNs) have become integral in safety-critical applications, thus raising concerns about their fault tolerance. Conventional hardware-dependent fault tolerance methods, such as Triple Modular Redundancy (TMR),…

The rise of instruction-tuned Large Language Models (LLMs) marks a significant advancement in artificial intelligence (AI) (tailored to respond to specific prompts). Despite their popularity, applying such models to debug security…

Deploying autonomous vision systems on edge devices faces a critical challenge: resource constraints prevent real-time and predictable execution of comprehensive safety tests. Existing validation methods depend on static datasets or manual…

Hardware Trojans (HTs) remain a critical threat because learning-based detectors often overfit to narrow trigger/payload patterns and small, stylized benchmarks. We introduce TrojanGYM, an agentic, LLM-driven framework that automatically…

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this…

The growing penetration of renewable and distributed generation is transforming power systems and challenging conventional protection schemes that rely on fixed settings and local measurements. Machine learning (ML) offers a data-driven…

In software development, the predominant emphasis on functionality often supersedes security concerns, a trend gaining momentum with AI-driven automation tools like GitHub Copilot. These tools significantly improve developers' efficiency in…

FPGAs are increasingly adopted in datacenter environments for their reconfigurability and energy efficiency. High-Level Synthesis (HLS) tools have eased FPGA programming by raising the abstraction level from RTL to untimed C/C++, yet…

Power grid fault diagnosis is a critical process hindered by its reliance on manual, error-prone methods. Technicians must manually extract reasoning logic from dense regulations and attempt to combine it with tacit expert knowledge, which…

Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often…

Numerous Fault Localisation (FL) and repair techniques have been proposed to address faults in Deep Learning (DL) models. However, their effectiveness in practical applications remains uncertain due to the reliance on pre-defined rules.…

Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for better performance, power, and area (PPA). However, existing methods are still far from realistic RTL optimization. Their…

Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the…