Latest news
-
AI Security via arXiv cs.CR
When File Ingestion Misleads Language Models: Measuring and Mitigating Divergences in Office Documents
arXiv:2611.05806v1 Announce Type: new Abstract: Office documents are now routinely uploaded to large language models (LLMs) for processing. However, an LLM does not…
-
Breaches via arXiv cs.CR
GRIDSHIELD: Verifiable Grid Feasibility and Manipulation Resistance in Privacy-Preserving Peer-to-Peer Energy Trading
arXiv:2611.05816v1 Announce Type: new Abstract: Blockchain-based peer-to-peer (P2P) energy markets let neighbors trade directly, but concentrate unchecked power in the…
-
AI Security via arXiv cs.CR
A Hybrid Approach for Automated Security Pattern Recovery
arXiv:2611.05823v1 Announce Type: new Abstract: Security-by-design emphasises integrating security into software design and development. Security pattern catalogues…
-
AI Security via arXiv cs.CR
Enforcing Accountable Disclosure in Confidential AI
arXiv:2611.05971v1 Announce Type: new Abstract: Advances in CPU and GPU confidential computing enable confidential AI, allowing LLMs to process user prompts without…
-
Breaches via arXiv cs.CR
CoordX Protocol: Peer to Peer Cryptographically Verified Shared Records
arXiv:2611.06034v1 Announce Type: new Abstract: People, companies and software agents often must work on shared records even when they do not trust each other. Today…
-
Vulnerabilities via arXiv cs.CR
PIMROP: A Feasibility Study of Return-Oriented Programming on Commercial Processing-in-Memory Architectures
arXiv:2611.06036v1 Announce Type: new Abstract: Processing-in-Memory places small programmable cores on the memory device, where they execute beside the DRAM banks and…
-
AI Security via arXiv cs.CR
Securing Web Agents with the Compile-Then-Execute Paradigm
arXiv:2611.06039v1 Announce Type: new Abstract: Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix…
-
Breaches via arXiv cs.CR
Reconciling Privacy with Provenance for Language Model Watermarks
arXiv:2611.06100v1 Announce Type: new Abstract: Watermarking has great potential for regulating the use of language models (LMs), but its deployment has been marred by…
- Advertisement
-
Threat Intel via arXiv cs.CR
SenTrojan: Revealing Analog Hardware Trojan Attacks on Sensors
arXiv:2611.06103v1 Announce Type: new Abstract: Sensors bridge the physical and digital worlds, making their integrity critical to cyber-physical system security…
-
AI Security via arXiv cs.CR
KVGuard: A KV Cache Safety Checker for LLM Serving Systems
arXiv:2611.06138v1 Announce Type: new Abstract: Modern LLM serving systems manage the KV cache through PagedAttention, a custom GPU allocator that partitions a single…
-
AI Security via arXiv cs.CR
Network Intrusion Forensic Detection System with Explainable Artificial Intelligence and Digital Chain of Custody
arXiv:2611.06173v1 Announce Type: new Abstract: Deploying an explainable intrusion detection model from a validated laboratory setting into a forensic workflow requires…
-
AI Security via arXiv cs.CR
Beyond the Landing Page: Website Blocking, Tracker Visibility, and Human Alignment in Automated Web Crawls
arXiv:2611.06197v1 Announce Type: new Abstract: Web tracking studies largely rely on automated crawlers, yet their measurements can differ from what people encounter…
-
Threat Intel via arXiv cs.CR
Explainable Anomaly Detection in 5G Networks through Continuous Time Graphs
arXiv:2611.06225v1 Announce Type: new Abstract: 5G networks increasingly resemble distributed systems in their design. It then becomes crucial to move beyond traditional…
-
Vulnerabilities via arXiv cs.CR
Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks
arXiv:2611.06257v1 Announce Type: new Abstract: Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they…
-
Threat Intel via arXiv cs.CR
Beyond Identity Creation: Bilinear Sybil Cost in Identities and Time
arXiv:2611.06268v1 Announce Type: new Abstract: Sybil defenses price the creation of an identity, yet influence goes, again and again, to active identities. We study the…
-
Threat Intel via arXiv cs.CR
Clear Human Web: Where a Person Vouches for Every Client
arXiv:2611.06286v1 Announce Type: new Abstract: The web cannot tell whether a request comes from a person or from a program. Sites have checked the network address and…
-
AI Security via arXiv cs.CR
A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code
arXiv:2611.06294v1 Announce Type: new Abstract: Large language model (LLM) coding assistants and agents construct a repository context before generating code. For…
-
Breaches via arXiv cs.CR
CoRTeC: A Differentially Private Release for Synthetic Tabular Data, Decodable by Any Generator
arXiv:2611.06342v1 Announce Type: new Abstract: The records that could train the most useful models, such as a hospital's patient files, are often the ones an…
-
Threat Intel via arXiv cs.CR
Shoot on (Core)Sight: Re-enabling Secure Debug on the RP2350 with Photon-Emission Microscopy and Laser Fault Injection
arXiv:2611.06386v1 Announce Type: new Abstract: Fault-resistant policy storage does not guarantee fault-resistant enforcement. We demonstrated this distinction on the…
-
Vulnerabilities via arXiv cs.CR
Towards Early Warning of Real-World Vulnerabilities: An Evidence-Aware Decoupled Method for CVSS Vector Prediction Based on Unstructured Disclosures
arXiv:2611.06477v1 Announce Type: new Abstract: Early assessment of Common Vulnerability Scoring System (CVSS) vectors from Open Source Intelligence (OSINT) can reduce…