🔌 Hardware Security - amy.throwaway.lovely · Scour

Turn Your Face Into An Attack Surface: Screen Attack Using Facial Reflections in Video Conferencing 🌐Protocol Fuzzing

arxiv.org·1d

A Hardware-Anchored Privacy Middleware for PII Sharing Across Heterogeneous Embedded Consumer Devices 📡Side Channels

arxiv.org·5h

3D-Stacked NMP, LLM Decoding, Systolic Array Microarchitecture, Multi-Core Scheduling ⚙️Compilers

arxiv.org·3d

MEV-ACE: Identity-Authenticated Fair Ordering for Proposer-Controlled MEV Mitigation 🐧Kernel Exploitation

arxiv.org·5h

Lightweight True In-Pixel Encryption with FeFET Enabled Pixel Design for Secure Imaging 📡Side Channels

arxiv.org·2d

TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense 📟Firmware Analysis

arxiv.org·5h

Sustainability Analysis of Prompt Strategies for SLM-based Automated Test Generation 🔀Concolic Execution

arxiv.org·4d

Arch: An AI-Native Hardware Description Language for Register-Transfer Clocked Hardware Design ⚙️Compilers

arxiv.org·2d

PG-MDP: Profile-Guided Memory Dependence Prediction for Area-Constrained Cores 🔍Memory Forensics

arxiv.org·5h

PHAROS: Pipelined Heterogeneous Accelerators for Real-time Safety-critical Systems With Deadline Compliance 🔒CFI

arxiv.org·2d

VCAO: Verifier-Centered Agentic Orchestration for Strategic OS Vulnerability Discovery 🐧Kernel Exploitation

arxiv.org·5h

Opal: Private Memory for Personal AI 🛡️Exploit Mitigations

arxiv.org·4d

Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery 🧮Symbolic Execution

arxiv.org·1d

A Full-Stack Performance Evaluation Infrastructure for 3D-DRAM-based LLM Accelerators 🔍Memory Forensics

arxiv.org·5h

Broken Quantum: A Systematic Formal Verification Study of Security Vulnerabilities Across the Open-Source Quantum Computing Simulator Ecosystem 🛡️Exploit Mitigations

arxiv.org·1d

Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation 🛡️Exploit Mitigations

arxiv.org·5h

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs 📟Firmware Analysis

arxiv.org·3d

Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering 🧩Intermediate Representation

arxiv.org·2d

SHIELD: A Segmented Hierarchical Memory Architecture for Energy-Efficient LLM Inference on Edge NPUs 🔍Memory Forensics

arxiv.org·5h

Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving 🔒CFI

arxiv.org·5h

Loading more...