Cheap AI-Assisted Reverse Engineering and What It Will Do
Generative AI is putting the law of reverse engineering (RE) under severe strain. Existing IP and technology laws assume
2026-10-28 归档
今日共收录 2009 条安全情报，包含 1141 个 CVE，471 篇安全通告，以及 100 篇研究论文。
← 返回归档列表The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service ope
PRISMA: Differentially Private Synthetic In-Car Telemetry via Differentiable Simulation
Differentially private synthesis of in-car energy consumption data is challenging because the output is high-dimensional
Merkle-Tree-Based Verifiable Public Data Auditing for Cloud Object Storage Using Smart Contracts
Owners of data in cloud object storage cannot directly check whether the provider still keeps every object unchanged. Ex
safeL4: Rethinking Safe-Language-Based Single Address Space Microkernels
Microkernels provide good features such as high security, safety, and flexibility, but their reliance on hardware-based
Trim: Fee Level Matters More Than Skew in Lightning Routing
Lightning routing nodes lend their channel balance for a posted fee. Operators' tools move that fee with the balance aro
False-Alarm Improvements and Detection Trade-Offs in Quantum Machine Learning for Intrusion Detection: A Reproducible Secondary Analysis
Published results in quantum machine learning for intrusion detection (QML-IDS) require joint interpretation of false-po
Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges
AI systems built around large models increasingly use experience and feedback to make persistent changes to models, prom
Intellectual Property Protection of Hyperdimensional Computing Classifiers: Black-Box Ownership Verification via Model Watermarking
Hyperdimensional computing (HDC) offers efficient learning and inference for resource-constrained systems, yet ownership
A Certified Robustness Framework for Backdoor Poisoning Attacks using $f$-Divergences
Machine learning systems trained on untrusted data are vulnerable to data and backdoor poisoning attacks, in which an ad
Attack logics, not outputs: Concept-based Property Attacks for Shortcut Elimination in Neural Networks
Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, such that minuscule malicious chan
Performance Guarantees for Permissionless Lending
We propose a lending protocol with far fewer risks than existing pool-based lending protocols (e.g., Aave, Compound). In
From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion
Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate inform
Compound Environmental Operating Stress and Cyber-Induced Pump Disruption in Water Distribution Networks: Matched Hydraulic Impacts, Service Continuity, and Sustained Recovery
Digitally controlled water distribution systems must maintain service during disruptions, yet restoring water delivery d
Denial of Service Attacks on Beam Allocation in Large LEO Constellations
We study the vulnerability of beam allocation approaches in large low-Earth-orbit (LEO) satellite constellations to adve
NovaFabric: A Black-Box Recorder for AI Agents with Sealed, Replayable, Diffable and Auditable Runs
An AI agent run is no longer a function call. It is a cascade of prompts, model calls, tool invocations, file and networ
CVM-Store: A Secure Storage System for Confidential Virtual Machines
Stateful cloud workloads require high-performance persistent storage when running on untrusted cloud infrastructure. Con
Does the Voynich Manuscript Mean Anything? Calibrated Tests Find Little Trace of Language
The Voynich manuscript is a fifteenth-century book in a script that no one can read. One account holds that its text mea
CyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance
Open-source projects now let AI agents review incoming code, but the code under review may itself come from an AI attack
Maximum-Likelihood Decoding of Gabidulin Codes Is NP-Hard Even in Dimension One
Fix a prime power q. We prove that deciding whether a received word y in Fnqm lies at rank distance at most n-2 from the