AutoPoly-HE: Autonomous Design of Polynomial Activations for Privacy-Preserving Encrypted Inference
Privacy-preserving machine learning has become critical for deploying artificial intelligence in sensitive domains such
2026-10-15 归档
今日共收录 805 条安全情报，包含 0 个 CVE，398 篇安全通告，以及 100 篇研究论文。
← 返回归档列表TrackShield: An Efficient Runtime Defense Against Availability Attacks on High-Performance Real-Time Multi-Object Tracking
High-performance camera-based perception pipelines must sustain per-frame real-time budgets on resource-constrained embe
Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
Agent skills are Markdown documents that a tool-using agent reads as instructions and then acts on with the privileges o
AegisAsync: Symbolic Async-Event Simulation for Risks in Python Asynchronous Programs
Security and robustness risks in Python async programs depend on event order, object identity, and execution after excep
$\mathsf{EFI}\Leftrightarrow\mathsf{1PRS}$
A series of recent works has established EFI pairs as the "minimal" assumption for quantum cryptography. Recently, Caval
Dynamic Attack Surfaces: A Queue of Branching Processes
Modern attack surfaces are inherently dynamic. Vulnerabilities emerge over time and they remain exposed to exploit until
ARACDE: Retrofitting Databases with ABAC using External Authorization Engines
This paper proposes a methodology for decoupling the authorization logic of a relational database from its core data man
Nudge the Judge: Uncovering Program Decision Hijacking in Real-World Jev Applications
System One models such as Jev change how software makes decisions by mapping open-ended semantic contexts into structure
DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), ye
Autonomous Cyber Operations Gym for Training and Evaluating AI Models for Defence
This paper proposes an Autonomous Cyber Operations (ACO) gym, a unified framework integrating high-fidelity network emul
Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries
Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activat
X.js: A Live Benchmark for Node.js Taint-Style Vulnerabilities
JavaScript vulnerabilities in npm packages pose a significant risk to the Node$.$js ecosystem, and a growing body of wor
Prompt-Segmentation Meets ROI Encryption: Fine-Grained Video Protection Based on Diffusion Isolation
Region-of-interest (ROI) selective encryption in H.265/HEVC aims to protect sensitive content while preserving the utili
Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model
Physical-layer spoofing attacks pose a critical threat to wireless localization systems by manipulating channel state in
Tanchun: Robust Flow-Based HTTP(S) DDoS Detection via Behavioral Attribute Guidance
HTTP(S) DDoS attacks have surged in frequency and scale, posing a significant threat to network security. Flow-based det
HULK: An Efficient Algorithm for Enabling Fast Bulk Bitwise Operations on Homomorphically Encrypted Data
A wide range of important cloud applications, e.g., database analytics, graph analytics, and genome analysis, spend a co
An Initial Study of Physiological Markers for Deepfake Speech Detection
Conventional deepfake speech detectors primarily target synthesis artifacts and often degrade under unseen attacks or re
Standing, Not Truth: Who May Say What About Whom in Agentic Selection
Software agents increasingly choose on a user's behalf among competing offerings described by the parties who benefit. A
Provenance and Authorization in Autobiographical Language Models
Autobiographical language models may draw on archives containing observations, quotations, emotional reports, and earlie
The Maximum Nonlinearity of 8-variable Balanced Boolean Functions is 116
Does there exist an 8-variable balanced Boolean function with nonlinearity 118? This is a famous and long-standing open