Imagen de Portada

Exploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Miah, Abdullah Arafat, Bi, Yu
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Artificial Intelligence Hardware Architecture
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study
por: Chai, Duo, et al.
Publicado: (2025)

PVF (Parameter Vulnerability Factor): A Scalable Metric for Understanding AI Vulnerability Against SDCs in Model Parameters
por: Jiao, Xun, et al.
Publicado: (2024)

Spatial Variation-Aware Read Disturbance Defenses: Experimental Analysis of Real DRAM Chips and Implications on Future Solutions
por: Yağlıkçı, Abdullah Giray, et al.
Publicado: (2024)

Understanding and Mitigating Covert Channel and Side Channel Vulnerabilities Introduced by RowHammer Defenses
por: Bostancı, F. Nisa, et al.
Publicado: (2025)

BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron
por: Miah, Abdullah Arafat, et al.
Publicado: (2026)

PVAC: A RowHammer Mitigation Architecture Exploiting Per-victim-row Counting
por: Kim, Jumin, et al.
Publicado: (2026)

SoK: Systematizing a Decade of Architectural RowHammer Defenses Through the Lens of Streaming Algorithms
por: Kim, Michael Jaemin, et al.
Publicado: (2025)

SENTAUR: Security EnhaNced Trojan Assessment Using LLMs Against Undesirable Revisions
por: Bhandari, Jitendra, et al.
Publicado: (2024)

TensorTEE: Unifying Heterogeneous TEE Granularity for Efficient Secure Collaborative Tensor Computing
por: Han, Husheng, et al.
Publicado: (2024)

TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion
por: Sreekumar, Saideep, et al.
Publicado: (2026)

3D Guard-Layer: An Integrated Agentic AI Safety System for Edge Artificial Intelligence
por: Kurshan, Eren, et al.
Publicado: (2025)

SecFSM: Knowledge Graph-Guided Verilog Code Generation for Secure Finite State Machines in Systems-on-Chip
por: Hu, Ziteng, et al.
Publicado: (2025)

VeriCWEty: Embedding enabled Line-Level CWE Detection in Verilog
por: Roy, Prithwish Basu, et al.
Publicado: (2026)

Enabling Efficient and Scalable DRAM Read Disturbance Mitigation via New Experimental Insights into Modern DRAM Chips
por: Yağlıkçı, Abdullah Giray
Publicado: (2024)

Cocoon: A System Architecture for Differentially Private Training with Correlated Noises
por: Kim, Donghwan, et al.
Publicado: (2025)

Analyzing and Exploiting Branch Mispredictions in Microcode
por: Mosier, Nicholas, et al.
Publicado: (2025)

On the Vulnerability of FHE Computation to Silent Data Corruption
por: Mu, Jianan, et al.
Publicado: (2026)

Supporting Secured Integration of Microarchitectural Defenses
por: Ramkrishnan, Kartik, et al.
Publicado: (2026)

LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models
por: Tahmasivand, Ahmad, et al.
Publicado: (2025)

Exploiting Inaccurate Branch History in Side-Channel Attacks
por: Zhu, Yuhui, et al.
Publicado: (2025)

Lite-BD: A Lightweight Black-box Backdoor Defense via Reviving Multi-Stage Image Transformations
por: Miah, Abdullah Arafat, et al.
Publicado: (2026)

Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators
por: Tyagi, Abhishek, et al.
Publicado: (2022)

RTL-Breaker: Assessing the Security of LLMs against Backdoor Attacks on HDL Code Generation
por: Mankali, Lakshmi Likhitha, et al.
Publicado: (2024)

RowPress Vulnerability in Modern DRAM Chips
por: Luo, Haocong, et al.
Publicado: (2024)

TroLL: Exploiting Structural Similarities between Logic Locking and Hardware Trojans
por: Liu, Yuntao, et al.
Publicado: (2023)

Lost and Found in Speculation: Hybrid Speculative Vulnerability Detection
por: Rostami, Mohamadreza, et al.
Publicado: (2024)

Exploiting the Lock: Leveraging MiG-V's Logic Locking for Secret-Data Extraction
por: Reimann, Lennart M., et al.
Publicado: (2024)

iThermTroj: Exploiting Intermittent Thermal Trojans in Multi-Processor System-on-Chips
por: Elahi, Mehdi, et al.
Publicado: (2025)

SpyHammer: Understanding and Exploiting RowHammer under Fine-Grained Temperature Variations
por: Orosa, Lois, et al.
Publicado: (2022)

An Early Experience with Confidential Computing Architecture for On-Device Model Protection
por: Abdollahi, Sina, et al.
Publicado: (2025)

Shield Bash: Abusing Defensive Coherence State Retrieval to Break Timing Obfuscation
por: Ramkrishnan, Kartik, et al.
Publicado: (2025)

Vulnerabilities in Partial TEE-Shielded LLM Inference with Precomputed Noise
por: Saini, Abhishek, et al.
Publicado: (2026)

DRAM-Profiler: An Experimental DRAM RowHammer Vulnerability Profiling Mechanism
por: Zhou, Ranyang, et al.
Publicado: (2024)

THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX
por: Dizani, Farshad, et al.
Publicado: (2025)

ShuffleV: A Microarchitectural Defense Strategy against Electromagnetic Side-Channel Attacks in Microprocessors
por: Narkthong, Nuntipat, et al.
Publicado: (2025)

EXAM: Exploiting Exclusive System-Level Cache in Apple M-Series SoCs for Enhanced Cache Occupancy Attacks
por: Xu, Tianhong, et al.
Publicado: (2025)

Securing DRAM at Scale: ARFM-Driven Row Hammer Defense with Unveiling the Threat of Short tRC Patterns
por: Joo, Nogeun, et al.
Publicado: (2025)

High-Speed VLSI Architectures for Modular Polynomial Multiplication via Fast Filtering and Applications to Lattice-Based Cryptography
por: Tan, Weihang, et al.
Publicado: (2021)

HE^2: A Communication-Light Heterogeneous Architecture for Efficient Fully Homomorphic Encryption
por: Shi, Shangyi, et al.
Publicado: (2026)

Low-Complexity Integer Divider Architecture for Homomorphic Encryption
por: Akherati, Sajjad, et al.
Publicado: (2024)