Intent-Hiding Jailbreaks: An Information-Theoretic Framework for...
arXiv:2610.02302v1 Announce Type: new Abstract: Recent work has shown that large language models (LLMs) can be vulnerable to jailbreak attacks in which harmful intent is obscured through composition...
View ArticleMIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication
arXiv:2610.02349v1 Announce Type: new Abstract: Inter-agent communication is central to Large Language Model Multi-Agent Systems (LLM-MAS), but it introduces an underexplored vulnerability:...
View ArticleHop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing...
arXiv:2610.02373v1 Announce Type: new Abstract: GraphRAG pipelines construct auxiliary structures during offline indexing--semantic summaries, hierarchical edges, and pre-computed scores--that...
View ArticleUnifying Privacy Accounting: Information Equivalence and Information Loss
arXiv:2610.02414v1 Announce Type: new Abstract: Differential privacy (DP) admits several notions, but the choice among them may affect both privacy analysis and utility. In this paper, we consider four...
View ArticleMitigating Private Data Leakage in LLMs with Whiteout
arXiv:2610.02418v1 Announce Type: new Abstract: Modern large language models (LLMs) are trained on massive, largely unfiltered datasets, including content scraped from nearly every accessible website...
View ArticleEvaluating and Improving the Robustness of Large Language Models to Input...
arXiv:2610.02432v1 Announce Type: new Abstract: Large language models (LLMs) in production systems face prompt injections, trojans (backdoors), and manipulation of automatic quality metrics. This...
View ArticleSoK: Stablecoins in the Quantum Era
arXiv:2610.02435v1 Announce Type: new Abstract: Stablecoins support payments, trading, collateral, and cross-chain settlement across the digital-asset ecosystem. They also concentrate value behind...
View ArticleSideKernel: A Usable microVM Sandbox for AI Coding Agents on macOS
arXiv:2610.02456v1 Announce Type: new Abstract: AI coding agents are untrusted system components, yet they require autonomy on the developer machines they run on. This contradiction is a security...
View ArticleCITADEL: CWE-Guided Insertion of Hardware Trojans via Analysis of DFG-Enabled...
arXiv:2610.02544v1 Announce Type: new Abstract: The increasing sophistication of Hardware Trojans (HTs) and system-level vulnerabilities poses significant risks to modern integrated circuits. However,...
View ArticleOut of Sync, Out of Sight: Phantom State Attacks against IIoT Intrusion...
arXiv:2610.02552v1 Announce Type: new Abstract: Machine learning-based intrusion detection systems (IDS) are critical for securing Industrial Internet of Things (IIoT) environments. Most adversarial...
View ArticlePincer: Resource Authorization for Agents using a Digital Twin
arXiv:2610.02569v1 Announce Type: new Abstract: Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for...
View ArticleFrom TS-SUF-2 to TS-SUF-4: Practical Security Enhancements for FROST2...
arXiv:2610.02805v1 Announce Type: new Abstract: Threshold signature schemes play a vital role in securing digital assets within blockchain and distributed systems. FROST2 stands out as a practical...
View ArticleRMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language...
arXiv:2610.02817v1 Announce Type: new Abstract: Large Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remains...
View ArticleContaining the Autonomous Operator: A Defense-in-Depth Framework and...
arXiv:2610.02861v1 Announce Type: new Abstract: Large language model (LLM) agents are moving from chat interfaces into infrastructure operations, where they read telemetry, call tools, generate and...
View ArticleAgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing...
arXiv:2610.02869v1 Announce Type: new Abstract: Autonomous penetration testing agents conduct multi-step attacks by continuously adapting their plans and actions to target responses. As a common...
View ArticleDigital Twin-Assisted Mapping of ICS Telemetry to ATT&CK for ICS with...
arXiv:2610.02955v1 Announce Type: new Abstract: Reconstructing adversarial behavior from Industrial Control System (ICS) telemetry is difficult because process observations reveal physical changes more...
View ArticleBeyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents
arXiv:2610.03014v1 Announce Type: new Abstract: Large language model (LLM)-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command...
View ArticleSecJev: Bringing Security Expertise to System One Decision Models
arXiv:2610.03073v1 Announce Type: new Abstract: Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed...
View ArticleSecuring Computer-Use Agents Against Branch Steering Attacks
arXiv:2610.03089v1 Announce Type: new Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt...
View ArticleThe Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs
arXiv:2610.03124v1 Announce Type: new Abstract: Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforced...
View Article
/fit-in/580x348/filters:format(webp)/english-betterindia/media/media_files/2026/09/30/project-neev-rural-education-2026-09-30-12-36-15.png)
