Latest news
-
Threat Intel via arXiv cs.CR
Agent-to-Agent Synthetic Social Engineering on the Web
arXiv:2610.33411v1 Announce Type: new Abstract: An AI agent can prepare an accurate report and still request an action its user has not authorized. Cooperation across…
-
Threat Intel via arXiv cs.CR
Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering
arXiv:2610.33437v1 Announce Type: new Abstract: Multi-trigger backdoor attacks, in which heterogeneous trigger mechanisms (e.g., patch, blend, warping, and the…
-
Vulnerabilities via arXiv cs.CR
Secure and Functional Code Generation with Self-Evaluation
arXiv:2610.33450v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate functionally correct code that remains insecure. Security-focused fine-tuning…
-
AI Security via arXiv cs.CR
From Instructions to Exploits: Applying Program Analysis to Malicious Agent Skills Across Natural Language and Code
arXiv:2610.33489v1 Announce Type: new Abstract: LLM-powered agents increasingly rely on third-party skills that combine natural-language instructions with executable…
-
AI Security via arXiv cs.CR
Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service
arXiv:2610.33525v1 Announce Type: new Abstract: Machine Learning as a Service (MLaaS) has become a popular paradigm for deploying AI applications. However, it raises…
-
Threat Intel via arXiv cs.CR
Security evaluation of 6G-oriented and O-RAN networks through targeted attacks
arXiv:2610.33526v1 Announce Type: new Abstract: The sixth generation (6G) of networks is supported by increased bandwidth, automation through the use of O-RAN…
-
AI Security via arXiv cs.CR
Who Verifies the Verifiers? Accountable Semantic Consensus for AI-Mediated Web Information Verification
arXiv:2610.33587v1 Announce Type: new Abstract: Large language models (LLMs) increasingly decide whether Web evidence supports online claims, often by voting over…
-
AI Security via arXiv cs.CR
ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift
arXiv:2610.33633v1 Announce Type: new Abstract: Agents select tools by copyable descriptions, which cannot establish which implementation runs. ProbeID compares…
- Advertisement
-
Vulnerabilities via arXiv cs.CR
VulDec: Vulnerability Detection in Binaries via Neural Decompilation
arXiv:2610.33716v1 Announce Type: new Abstract: Automated vulnerability detection in binary executables is challenging due to the lack of source code and the limited…
-
AI Security via arXiv cs.CR
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
arXiv:2610.33732v1 Announce Type: new Abstract: Generative AI and large language models (LLMs) are moving into the Internet of Things, yet most deployments assume cloud…
-
AI Security via arXiv cs.CR
Ring-0 by Default: Agents as Operating Systems (AaOS)
arXiv:2610.33753v1 Announce Type: new Abstract: LLM agents now read and write files, start processes and subagents, fetch network content, load third-party extensions…
-
Vulnerabilities via arXiv cs.CR
Enhancing LLM-Based Vulnerability Detection via Representation-Aware Logical Ensemble
arXiv:2610.33756v1 Announce Type: new Abstract: Automated vulnerability detection in C source code is a long-standing challenge, as traditional static analysis tools…
-
Threat Intel via arXiv cs.CR
Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses
arXiv:2610.33849v1 Announce Type: new Abstract: Query-time filters that screen each retrieved document before it reaches the generator are the dominant published defense…
-
AI Security via arXiv cs.CR
Securing Edge & Physical AI: Post-Quantum IoT Blockchain for Mission-Critical Cyber-Physical Agents
arXiv:2610.33862v1 Announce Type: new Abstract: Distributed Cyber-Physical Systems (CPS) and Edge AI networks increasingly depend on public-key authentication and…
-
Threat Intel via SANS Internet Storm Center
ISC Stormcast For Tuesday, October 27th, 2026 https://isc.sans.edu/podcastdetail/10152, (Tue, Oct 27th)
(c) SANS Internet Storm Center. https://isc.sans.edu Creative Commons Attribution-Noncommercial 3.0 United States License.
-
Vulnerabilities via Chrome Releases
Long Term Support Channel Update for ChromeOS
A new LTS-150 version 150.0.7871.287(Platform Version: 16700.68.0), is being rolled out for most ChromeOS devices.
-
AI Security via Cloud Security Alliance
Cloud Security Alliance Launches STAR for AI Level 2 to Strengthen AI Governance and Trust
STAR for AI Level 2 allows organizations to extend existing industry certifications and assurance frameworks into the AI domain SEATTLE – Oct. 27, 2026 — Organizations…
-
Threat Intel via SecurityWeek
Cybersecurity Issue Forces a Major New Mexico Hospital to Divert Patients and Close Clinics
The University of New Mexico Health System told people not to show up at its main hospital in Albuquerque and canceled appointments at more than 30 clinics.
-
Vulnerabilities via Tenable
Brotli2Shell: Frequently asked questions for Google Brotli decoder vulnerability (CVE-2026-111497)
Researchers have demonstrated remote code execution through CVE-2026-111497, an out-of-bounds write in Google's Brotli decoder library, and public proofs-of-concept…
-
Vulnerabilities via oss-security
Re: PHP 5.4.23 (custom 5.4-5.6) backported patch for PHP2Shell OOM vulnerability (CVE-2026-109618)
Posted by Peter Wolanin on Oct 26 The PPA we use https://launchpad.net/~ondrej/+archive/ubuntu/php had a PHP 5.6 back port the same day. Have you compared your patch to…