Related papers: RangeGuard: Efficient, Bounded Approximate Error C…

IR-based fault localization approaches achieves promising results when locating faulty files by comparing a bug report with source code. Unfortunately, they become less effective to locate faulty methods. We conduct a preliminary study to…

Recently, neural networks have spread into numerous fields including many safety-critical systems. Neural networks are built (and trained) by programming in frameworks such as TensorFlow and PyTorch. Developers apply a rich set of…

Overparametrized neural networks trained by gradient descent (GD) can provably overfit any training data. However, the generalization guarantee may not hold for noisy data. From a nonparametric perspective, this paper studies how well…

Neural Networks are currently one of the most widely deployed machine learning algorithms. In particular, Convolutional Neural Networks (CNNs), are gaining popularity and are evaluated for deployment in safety critical applications such as…

Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications. Existing solutions for the clutter versus multi-source radar classification task are limited in…

In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in many distributed DNN training scenarios, including the recently popular federated…

The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from their iterative and parallel generation mechanisms. In this…

Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…

Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs,…

Systolic array-based deep neural network (DNN) accelerators have recently gained prominence for their low computational cost. However, their high energy consumption poses a bottleneck to their deployment in energy-constrained devices. To…

Recurrent neural networks (RNNs) are a powerful model for sequential data. End-to-end training methods such as Connectionist Temporal Classification make it possible to train RNNs for sequence labelling problems where the input-output…

Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from the final…

We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND…

Large Language Models (LLMs) have gained significant traction in various applications, yet their capabilities present risks for both constructive and malicious exploitation. Despite extensive training and fine-tuning efforts aimed at…

Due to the scarcity and unpredictable nature of defect samples, industrial anomaly detection (IAD) predominantly employs unsupervised learning. However, all unsupervised IAD methods face a common challenge: the inherent bias in normal…

Deep Neural Networks (DNNs) have been widely used in software making decisions impacting people's lives. However, they have been found to exhibit severe erroneous behaviors that may lead to unfortunate outcomes. Previous work shows that…

State-of-the-art DRAM read disturbance mitigations rely on the read disturbance threshold (RDT) (e.g., the number of aggressor row activations needed to induce the first read disturbance bitflip) to securely and performance- and…

Retrieval-Augmented Code Generation (RACG) leverages external knowledge to enhance Large Language Models (LLMs) in code synthesis, improving the functional correctness of the generated code. However, existing RACG systems largely overlook…

Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus unsuitable for deployment on resource-constrained devices…

Deep Neural Networks (DNNs) continue to grow in complexity with Large Language Models (LLMs) incorporating vast numbers of parameters. Handling these parameters efficiently in traditional accelerators is limited by data-transmission…