arXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive...
The paper demonstrates that undervolting GPUs during CNN training introduces stochastic faults that act as implicit regularization, improving adversarial robustness while reducing power consumption. Experiments on LeNet, VGG-6, and MobileNetV3 trained on MNIST and CIFAR-10 show that undervolted models consistently outperform nominal-voltage models in both standard and adversarial training regimes. The approach offers a hardware-level defense that requires no algorithmic changes and yields significant energy savings due to the quadratic relationship between dynamic power and supply voltage.
The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.
TEE-X is a TEE‑aware acceleration framework designed to run large vision models, such as Vision Transformers, entirely within Trusted Execution Environments. It introduces a sensitivity‑aware modularization technique and vectorization to overcome memory constraints and latency challenges on edge devices. The framework is validated on OP‑TEE for Arm TrustZone and optimized for the NVIDIA Jetson AGX Xavier, achieving GPU‑level inference latency with minimal accuracy‑latency trade‑offs.
arXiv:2607. 12868v1 Announce Type: cross Abstract: Deep learning systems often fail due to subtle implementation faults that alter training behavior.
Deploying deep learning models on edge CPUs is bottlenecked by computational and memory constraints. Mixed-precision quantization promises to reduce inference latency while preserving accuracy. Howeve...
The paper introduces Right In-Place (RiP) convolution, a memory‑efficient strategy that corrects and generalizes previous in‑place convolution formulations to arbitrary stride, dilation, padding, and rectangular kernels. RiP aligns each layer’s input and output within a shared workspace, enabling safe, row‑major access with minimal memory overhead. Experiments on 10,000 random layers and 84 layers from 25 architectures show no corruption, matching or improving on existing herringbone workspaces while reducing memory usage by up to 24.8% and lowering peak activation memory on Raspberry Pi Pico MCUs by 12.5–33.3% without affecting cycle counts.
TreeFI is a value‑aware statistical fault‑injection technique for FP32 single‑bit faults in deep neural network activations and weights. It partitions each layer’s value distribution into intervals with similar expected bit‑flip behavior using regression trees, then allocates injections across these intervals based on their relevance for failure‑rate estimation. This stratified approach preserves target confidence and error margins while dramatically reducing the required injection budget—up to 72.1× for activations and 11.2× for weights compared to existing baselines.
arXiv:2606. 02267v1 Announce Type: new Abstract: The vulnerability of deep neural networks to adversarial examples poses a significant challenge for real-world deployment.
arXiv:2608. 11770v1 Announce Type: cross Abstract: Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis.
The study examines how reducing the width of deep neural networks through structured pruning affects their robustness to Single Event Upsets (SEUs). By iteratively pruning baseline models and conducting fault-injection tests at each stage, the authors find that while pruning increases per-inference sensitivity to bit-flips, the shorter execution time offsets this, lowering the overall SEU probability. Consequently, structured pruning can deliver energy and latency savings without compromising reliability for space-based AI systems.
arXiv:2304. 03388v2 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have become ubiquitous for their ability to solve problems across various domains, including computer vision, natural language processing, and speech recognition.