PrivacyGuard: Source-Linked Sanitization and Locally Resolvable PII References for Cloud GUI Agents
Cloud graphical user interface (GUI) agents send instructions and screenshots to remote planners, exposing personally id
2026-10-14 归档
今日共收录 1875 条安全情报，包含 867 个 CVE，609 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Digital-Twin-Referenced Belief-Guided Q-Learning for Jammer Identification and Beam-Power Control in a mmWave Model
Digital Twin (DT) combined with reinforcement learning (RL) can support adaptive resource allocation and security-aware
CT0: Cybersecurity Transformer
General-purpose frontier models are large, expensive to run, and increasingly reluctant to engage with authorised defens
Differential Privacy Protected Preference Alignment on Survey Derived Data
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive
Revisiting Fast Tendermint: An Agreement Violation and Two Repairs
Fast Tendermint reduces Tendermint's good-case latency to two communication steps for n>=5f+1. We show that its publishe
Not All Challenges Are Equal: Evaluating Interactive Liveness Detection Against Real-Time Face Swaps
Remote identity verification assumes that a camera stream shows a live person, yet public real-time face-swap tools can
Risk-aware Road-network Trajectory Synthesis under Local Differential Privacy
Road-network trajectory synthesis under local differential privacy (LDP) enables mobility data analysis without uploadin
Doctor Trigger: A Framework for Release-Bound Face Verification
Face swapping and generative editing enable realistic facial manipulation, while online redistribution complicates publi
ML-Assisted Power Side-Channel Attacks on ML Accelerators in Shared FPGAs
Cloud providers offer on-demand access to Field-Programmable Gate Arrays (FPGAs), and multi-tenant FPGAs let multiple us
Confidential Error-Correcting Codes
We introduce Confidential Error-correcting Codes (CECs), a new cryptographic primitive that enables reliable decoding fr
Adversarial Robustness of Camera-Radar Sensor Fusion for Autonomous Driving
Autonomous driving (AD) relies on multi-sensor perception to interpret the surrounding environment. However, the robustn
CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents
Authorization checks at individual tool calls do not reveal how long earlier authority remains usable. We study this lif
Hardware-Assisted Multi-Stage Ransomware Detection with Adaptive Machine Learning
Ransomware is a fast-escalating privacy threat causing significant financial and data losses worldwide. As attacks grow
Forensic Text Recovery from Document Thumbnails Using Text-Aware U-Net
Forensic analysis of low-resolution Word thumbnails presents a significant challenge because these artifacts may constit
RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use
False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contrac
The Role of Generative Artificial Intelligence in Testing and Automation of Open RAN Systems: GNG-OTA Framework
Open Radio Access Networks (O-RAN) empower operators with choice and customization through their disaggregated and inter
To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse
Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generate
Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging
Deep learning is now central to radiology, helping detect changes on X-rays, CTs, and MRIs. However, these systems are h
Riemannian Suppression of Cross-Session Identity Leakage in Motor-Imagery EEG
Electroencephalography (EEG) recorded for motor-imagery (MI) brain-computer interfaces (BCIs) carries subject-identifyin
Fetch Me If You Can: A Comprehensive Analysis of Fetch Metadata
Effective server-side defenses against cross-site attacks depend on understanding the context in which browser requests