Image de couverture de livre

PVF (Parameter Vulnerability Factor): A Scalable Metric for Understanding AI Vulnerability Against SDCs in Model Parameters

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jiao, Xun, Lin, Fred, Dixit, Harish D., Coburn, Joel, Pandey, Abhinav, Wang, Han, Ramesh, Venkat, Huang, Jianyu, Xu, Wang, Moore, Daniel, Sankar, Sriram
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security Artificial Intelligence Hardware Architecture Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

RowPress Vulnerability in Modern DRAM Chips
par: Luo, Haocong, et autres
Publié: (2024)

Understanding and Mitigating Covert Channel and Side Channel Vulnerabilities Introduced by RowHammer Defenses
par: Bostancı, F. Nisa, et autres
Publié: (2025)

Unicorn-CIM: Uncovering the Vulnerability and Improving the Resilience of High-Precision Compute-in-Memory
par: Li, Qiufeng, et autres
Publié: (2025)

Analyzing the Single Event Upset Vulnerability of Binarized Neural Networks on SRAM FPGAs
par: Souvatzoglou, Ioanna, et autres
Publié: (2024)

On the Vulnerability of FHE Computation to Silent Data Corruption
par: Mu, Jianan, et autres
Publié: (2026)

Lost and Found in Speculation: Hybrid Speculative Vulnerability Detection
par: Rostami, Mohamadreza, et autres
Publié: (2024)

Vulnerabilities in Partial TEE-Shielded LLM Inference with Precomputed Noise
par: Saini, Abhishek, et autres
Publié: (2026)

LLM-DSE: Searching Accelerator Parameters with LLM Agents
par: Wang, Hanyu, et autres
Publié: (2025)

DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism
par: Zhou, Ranyang, et autres
Publié: (2024)

A Computing-in-Memory-based One-Class Hyperdimensional Computing Model for Outlier Detection
par: Wang, Ruixuan, et autres
Publié: (2023)

Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study
par: Chai, Duo, et autres
Publié: (2025)

Chiplets on Wheels: Review Paper on Holistic Chiplet Solutions for Autonomous Vehicles
par: Narashiman, Swathi, et autres
Publié: (2024)

From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing
par: Zhao, Yushu, et autres
Publié: (2025)

Fast Parameter Optimization of Delayed Feedback Reservoir with Backpropagation and Gradient Descent
par: Ikeda, Sosei, et autres
Publié: (2025)

Optimising GPGPU Execution Through Runtime Micro-Architecture Parameter Analysis
par: Sarda, Giuseppe M., et autres
Publié: (2024)

Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators
par: Tyagi, Abhishek, et autres
Publié: (2022)

ApproxGNN: A Pretrained GNN for Parameter Prediction in Design Space Exploration for Approximate Computing
par: Vlcek, Ondrej, et autres
Publié: (2025)

On the Thermal Vulnerability of 3D-Stacked High-Bandwidth Memory Architectures
par: Elahi, Mehdi, et autres
Publié: (2025)

μRL: Discovering Transient Execution Vulnerabilities Using Reinforcement Learning
par: Tol, M. Caner, et autres
Publié: (2025)

RoSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learning
par: Cao, Weidong, et autres
Publié: (2024)

An Architectural Error Metric for CNN-Oriented Approximate Multipliers
par: Liu, Ao, et autres
Publié: (2024)

TrainDeeploy: Hardware-Accelerated Parameter-Efficient Fine-Tuning of Small Transformer Models at the Extreme Edge
par: Wang, Run, et autres
Publié: (2026)

Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems
par: Yamamoto, Yuji, et autres
Publié: (2026)

Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor
par: Miah, Abdullah Arafat, et autres
Publié: (2024)

The BRAM is the Limit: Shattering Myths, Shaping Standards, and Building Scalable PIM Accelerators
par: Kabir, MD Arafat, et autres
Publié: (2024)

LLM-Aided Testbench Generation and Bug Detection for Finite-State Machines
par: Bhandari, Jitendra, et autres
Publié: (2024)

BitROM: Weight Reload-Free CiROM Architecture Towards Billion-Parameter 1.58-bit LLM Inference
par: Zhang, Wenlun, et autres
Publié: (2025)

A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference
par: Wang, Chuanning, et autres
Publié: (2024)

SPEED: A Scalable RISC-V Vector Processor Enabling Efficient Multi-Precision DNN Inference
par: Wang, Chuanning, et autres
Publié: (2024)

Pedagogically Motivated and Composable Open-Source RISC-V Processors for Computer Science Education
par: McDougall, Ian, et autres
Publié: (2025)

On-Device Qwen2.5: Efficient LLM Inference with Model Compression and Hardware Acceleration
par: Xiang, Maoyang, et autres
Publié: (2025)

LEAP: LLM Inference on Scalable PIM-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism
par: Wang, Yimin, et autres
Publié: (2025)

D-Legion: A Scalable Many-Core Architecture for Accelerating Matrix Multiplication in Quantized LLMs
par: Abdelmaksoud, Ahmed J., et autres
Publié: (2026)

C2HLSC: Can LLMs Bridge the Software-to-Hardware Design Gap?
par: Collini, Luca, et autres
Publié: (2024)

UpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications
par: Rajasukumar, Andronicus, et autres
Publié: (2024)

SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions
par: Bhandari, Jitendra, et autres
Publié: (2024)

ConSmax: Hardware-Friendly Alternative Softmax with Learnable Parameters
par: Liu, Shiwei, et autres
Publié: (2024)

ISAAC: Intelligent, Scalable, Agile, and Accelerated CPU Verification via LLM-aided FPGA Parallelism
par: Sun, Jialin, et autres
Publié: (2025)

From Natural Language to Silicon: The Representation Bottleneck in LLM Hardware Design
par: Fu, Weimin, et autres
Publié: (2026)

QED: Scalable Verification of Hardware Memory Consistency
par: Ravi, Gokulan, et autres
Publié: (2024)