Latest news
-
AI Security via Dark Reading
UAE Transitions 50% of Gov't Services to Agentic AI
The United Arab Emirates says it's creating a foundation of security and safety as it transforms its public service footprint.
-
AI Security via Help Net Security
AI coding boom exposes cracks in cloud development
Developers are encountering bugs, testing delays and disruptions in shared cloud environments as AI increases the volume of code they produce, according to LocalStack’s…
-
AI Security via The Hacker News
China-Linked Hackers Use ARTEX AI Agents in ConnectWise Supply Chain Attack
Microsoft on Wednesday disclosed that a China state-aligned actor dubbed Storm-0940 was behind the recent supply chain compromise of the ConnectWise Cloud Backup…
-
AI Security via Help Net Security
AI agent observability is struggling to keep up with hallucinations
Sixty-two percent of IT and engineering professionals now rely on AI agents frequently to work out why their systems broke, and more than half have no way to measure…
-
Threat Intel via arXiv cs.CR
Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain
arXiv:2610.28794v1 Announce Type: new Abstract: Software supply chain attacks continue to be on the rise, exploiting the trust that helps open source ecosystems thrive…
-
AI Security via arXiv cs.CR
How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery
arXiv:2610.28802v1 Announce Type: new Abstract: How much does an agent harness affect vulnerability discovery, and does its value depend on the model? We study 24…
-
AI Security via arXiv cs.CR
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
arXiv:2610.28810v1 Announce Type: new Abstract: The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt…
-
AI Security via arXiv cs.CR
AI Security Literacy: Ecosystem-based Competency Framework and K-12 Learning Platform
arXiv:2610.28859v1 Announce Type: new Abstract: Adoption of artificial intelligence in K-12 schools has outpaced guidance for students, teachers, and administrators…
- Advertisement
-
AI Security via arXiv cs.CR
Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning
arXiv:2610.28966v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed in multi-agent systems (MAS) to accomplish complex tasks…
-
Threat Intel via arXiv cs.CR
Beyond Tokens: NumAnchor for Address-Grounded Numeric Operand Representation in Assembly Language Models
arXiv:2610.29027v1 Announce Type: new Abstract: Assembly language models (ALMs) are becoming important for automated binary analysis, yet their token-level interfaces…
-
Threat Intel via arXiv cs.CR
Regular Syndrome Decoding Is Easier Than Previously Estimated
arXiv:2610.29175v1 Announce Type: new Abstract: The Regular Syndrome Decoding (RSD) problem is a structured variant of classical Syndrome Decoding and underlies a…
-
AI Security via arXiv cs.CR
Correlated Failures of AI Approval Monitors
arXiv:2610.29178v1 Announce Type: new Abstract: Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it…
-
Vulnerabilities via arXiv cs.CR
Cryptanalysis and Repair of "Decentralized Multi-authority ABE for NC$^1$ from BDH"
arXiv:2610.29224v1 Announce Type: new Abstract: We present a plaintext-recovery attack on the decentralized multi-authority attribute-based encryption construction of…
-
Threat Intel via arXiv cs.CR
MASAR: Multi-stage Attack Surface Analysis and Reasoning Framework for Telecom Networks
arXiv:2610.29343v1 Announce Type: new Abstract: The increasing complexity of modern telecommunications networks introduces security challenges that require systematic…
-
Vulnerabilities via arXiv cs.CR
Where AI Vulnerability Discovery Harnesses Go Quiet: Structural False Negatives and Hidden Vulnerabilities
arXiv:2610.29379v1 Announce Type: new Abstract: LLM-based vulnerability discovery harnesses can miss real, reachable vulnerabilities because of how the harness around…
-
AI Security via arXiv cs.CR
CertMoE: Robustness Certification for Mixture-of-Experts LLMs via Routing-Aware Smoothing
arXiv:2610.29395v1 Announce Type: new Abstract: Provable robustness is a cornerstone of trustworthy machine learning, aiming to guarantee model predictions under…
-
Threat Intel via arXiv cs.CR
VMSpec: A Decompiler-based Approach against Virtual Machine Obfuscation
arXiv:2610.29566v1 Announce Type: new Abstract: Malicious actors frequently obfuscate their code to hinder investigative reverse engineering efforts. Among the most…
-
Breaches via arXiv cs.CR
Beyond Policy Engines: Binding-Complete Execution Admission
arXiv:2610.29701v1 Announce Type: new Abstract: Policy engines determine whether evaluated policies permit a request, but a correct ALLOW decision does not establish…
-
AI Security via arXiv cs.CR
Prompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital Investigations
arXiv:2610.29747v1 Announce Type: new Abstract: Large language models (LLMs) are entering digital forensics as examination assistants and autonomous agents. Digital…
-
Breaches via arXiv cs.CR
Location-of-interest vs. Current-location Privacy in Multi-hop Communication
arXiv:2610.29772v1 Announce Type: new Abstract: Consider a standard multi-hop wireless radio network in which nodes relay messages for one another. While the contents of…