Stress-Testing Structure-Aware Calibration of Malware Graph Neural Networks...
arXiv:2609.28517v1 Announce Type: new Abstract: Post-hoc malware calibrators can condition confidence on graph structure, but their structural inputs may leave the support represented by validation...
View ArticleAn Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting
arXiv:2609.28528v1 Announce Type: new Abstract: The goal of this note is to give a detailed proof, to the best of our understanding, of the recent presentation by Harrison and Leeman...
View ArticlePrivacy Leakage Through AI-mediated Analysis of Smartphone Data
arXiv:2609.28537v1 Announce Type: new Abstract: Over the past thirty years, the online advertising industry built a large-scale data collection ecosystem, with the goal of tracking a user's online...
View ArticleWho Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
arXiv:2609.28559v1 Announce Type: new Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an...
View ArticleDon't Read the Log: Execution Traces Contaminate Verifiers in...
arXiv:2609.28564v1 Announce Type: new Abstract: Agentic video-generation systems close a loop between a generator and a verifier: an LLM plans shots, calls a text-to-video model, and a multimodal judge...
View ArticleWhere Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents
arXiv:2609.28572v1 Announce Type: new Abstract: Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution...
View ArticlePersistent Billable State: Denial-of-Wallet Attacks and Defenses in...
arXiv:2609.28585v1 Announce Type: new Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model...
View ArticleAgent Approval Laundering: Transitive Effects Beyond the Approved Invocation
arXiv:2609.28586v1 Announce Type: new Abstract: Coding-agent approval interfaces bind a human decision to a command or tool call, while developer tools execute the transitive workflow that invocation...
View ArticleBRFID: Toward Byzantine-Robust Federated Intrusion Detection
arXiv:2609.28599v1 Announce Type: new Abstract: Flipping 60\% of training labels from a single Byzantine client using label-flipping model poisoning self-degrades an attacker's own federated detection...
View ArticleCONCURDEP: Event-Guided Analysis of Dependency Invalidation in CPython...
arXiv:2609.28608v1 Announce Type: new Abstract: Removing CPython's Global Interpreter Lock (GIL) exposes native code to concurrency absent from ordinary C types. Mutation or re-entry can revoke a...
View ArticleDecision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic...
arXiv:2609.28613v1 Announce Type: new Abstract: Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these...
View Article"What I See is What I Hear": Deepfake Detection Across Diverse Hearing Abilities
arXiv:2609.28659v1 Announce Type: new Abstract: The proliferation of audiovisual deepfakes has lowered the cost of fraud, impersonation, and misinformation, but their success ultimately depends on...
View ArticlezkSAS: Practical Zero-Knowledge Proofs for Verifiable Spectrum Access Management
arXiv:2609.28699v1 Announce Type: new Abstract: Dynamic Spectrum Access (DSA) through the Spectrum Access Systems (SAS) elevates spectral efficiency, yet existing centralized models face allocation...
View ArticleUnmasking Shortcut Learning in IoT Intrusion Detection: A Forensic,...
arXiv:2609.28725v1 Announce Type: new Abstract: Machine learning-based Network Intrusion Detection Systems often report near-perfect performance on IoT benchmarks. However, whether these models learn...
View ArticleBlockchain-Enabled Artificial Intelligence and AI Agents for Secure Data...
arXiv:2609.28843v1 Announce Type: new Abstract: Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonomous...
View ArticleWhen Do Differentially Private Inputs Protect Graph Shift Operators?
arXiv:2609.28899v1 Announce Type: new Abstract: We study the differential privacy (DP) of a graph shift operator (GSO) when an analyst observes the output of a graph filter. In particular, we study the...
View ArticleCodetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion
arXiv:2609.28900v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) are increasingly deployed in high-stakes settings such as finance, healthcare, and software...
View ArticleOn the Effectiveness of Kernel-Level Evidence for Agent Security
arXiv:2609.28915v1 Announce Type: new Abstract: LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost...
View ArticleCalibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV...
arXiv:2609.28940v1 Announce Type: new Abstract: Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those same...
View ArticleDistillGuard: Malicious NPM Package Detection and API Attack Chain Analysis...
arXiv:2609.28996v1 Announce Type: new Abstract: The Node.js ecosystem heavily relies on NPM packages, and software supply chain attacks targeting malicious NPM packages are rampant. Malicious code...
View Article
