Library

Subject
Tags

1,355 matches · Security and Verification in Computing

#
001A Privacy-Preserving Middleware Architecture for Detecting Prompt Injection and Sensitive Data Exposure in Large Language Model InteractionsOpenAlexPaperAdam Ait Hsine, Abdullahi Arabo4 days ago
002Prompting Rules That Reduce Codex Mojibake Accidents on Windows (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
003Prompting Rules That Reduce Codex Mojibake Accidents on Windows (archived 2026-07-27)OpenAlexPaperGo Komura4 days ago
004The Open Planner: Certified Analytical Plans from Untrusted Searchers — A Research Program NoteOpenAlexPaperHuayin Wang4 days ago
005The Open Planner: Certified Analytical Plans from Untrusted Searchers — A Research Program NoteOpenAlexPaperHuayin Wang4 days ago
006The Open Planner: Certified Analytical Plans from Untrusted Searchers — A Research Program NoteOpenAlexPaperHuayin Wang4 days ago
007The Open Planner: Certified Analytical Plans from Untrusted Searchers — A Research Program NoteOpenAlexPaperHuayin Wang4 days ago
008Circuit-Aware LoRA: Reducing Hallucinations in Security LLMsOpenAlexPaperYahya Saqban7 days ago
009Circuit-Aware LoRA: Reducing Hallucinations in Security LLMsOpenAlexPaperYahya Saqban7 days ago
010Hayula: The Complete Vision — Democratizing Cybersecurity AI on Commodity HardwareOpenAlexPaperYahya Saqban7 days ago
011Hayula: The Complete Vision — Democratizing Cybersecurity AI on Commodity HardwareOpenAlexPaperYahya Saqban7 days ago
012A System-Level Security Analysis and Roadmap for Large Language Model-Based SystemsOpenAlexPaperSelin Şaşal, Özgü CanJul 22
013AI / LLM Nomologically Gated Capability GrowthOpenAlexPaperSławomir KrakowskiJul 21
014AI / LLM Nomologically Gated Capability GrowthOpenAlexPaperSławomir KrakowskiJul 21
015Uncertainty-Aware Evidential Adversarial Defense for Cloud Intrusion Detection under GAN-Based Evasion AttacksOpenAlexPaperJiawen Luo, Samuel PriceJul 20
016Cybersecurity Topology: Geometric Defenses Beyond RLHF, Token Filtering, and JailbreaksOpenAlexPaperVui Kien LiauJul 19
017Cybersecurity Topology: Geometric Defenses Beyond RLHF, Token Filtering, and JailbreaksOpenAlexPaperVui Kien LiauJul 19
018Example Of Cross-Chain Grammar Unification: Detour And ZFlip At S=0OpenAlexPaperWilliam J. RichardsonJul 19
019Example Of Cross-Chain Grammar Unification: Detour And ZFlip At S=0OpenAlexPaperWilliam J. RichardsonJul 19
020The Relational Theory of Information IntegrityOpenAlexPaperT. S. EdenJul 19
021The Relational Theory of Information IntegrityOpenAlexPaperT. S. EdenJul 19
022Delegated Authorization in Autonomous Systems - Akash NarayanOpenAlexPaperAkash NarayanJul 18
023Delegated Authorization in Autonomous Systems - Akash NarayanOpenAlexPaperAkash NarayanJul 18
024MC-PoisonVerif: Model Checking-Driven Poisoning Attack Formal Verification AlgorithmOpenAlexPaperCongdong Lv, Yupeng Song et al.Jul 18
025Best Token Use Path (BTUP): Client-Side Traffic Engineering for Cost-Aware LLM InferenceOpenAlexPaperFrancesco TramaJul 17
026Hardware-rooted attestation for AI-agent evidence: composing IETF RATS with action evidence packagesOpenAlexPaperAnton SokolovJul 17
027Best Token Use Path (BTUP): Client-Side Traffic Engineering for Cost-Aware LLM InferenceOpenAlexPaperFrancesco TramaJul 16
028Trisduction System Role: The Kinetic Preloader and the RAM-Founded Computational KernelOpenAlexPaperMohammad IslamJul 16
029Trisduction System Role: The Kinetic Preloader and the RAM-Founded Computational KernelOpenAlexPaperMohammad IslamJul 16
030Confused Deputy Attack Against Model Context ProtocolOpenAlexPaperZhiyuan Li, Jingzheng Wu et al.Jul 15
031Governance Before Generation: An empirical N=100 A/B measurement of answer-entitlement and context governance on Gemma 4 12BOpenAlexPaperTaiko ToedaJul 14
032Governance Before Generation: An empirical N=100 A/B measurement of answer-entitlement and context governance on Gemma 4 12BOpenAlexPaperTaiko ToedaJul 14
033Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model FamiliesOpenAlexPaperDushyant SharmaJul 14
034Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model FamiliesOpenAlexPaperDushyant SharmaJul 14
035IntentLock: A Deterministic Intent-to-Commit Control and Evidence Architecture for AI-Assisted Software DevelopmentOpenAlexPaperAgim HaxhijahaJul 14
036IntentLock: A Deterministic Intent-to-Commit Control and Evidence Architecture for AI-Assisted Software DevelopmentOpenAlexPaperAgim HaxhijahaJul 14
037Best Token Use Path (BTUP): Client-Side Traffic Engineering for Cost-Aware LLM InferenceOpenAlexPaperFrancesco TramaJul 13
038Toward a Principled Framework for Agent Safety MeasurementOpenAlexPaperShuyi Lin, Anshuman Suri et al.Jul 13
039ARGUS: Adversarial Principal Hierarchy Testing and Constitutional Hardening Framework for Multi-Agent SystemsOpenAlexPaperVenkata Narendra NukaJul 11
040ARGUS: Adversarial Principal Hierarchy Testing and Constitutional Hardening Framework for Multi-Agent SystemsOpenAlexPaperVenkata Narendra NukaJul 11
041Dual-Gate Evidence Rails for Attested Agentic AI: Deny-Before-Inference and Permit-Before-Commit Control of External EffectsOpenAlexPaperY N LeeJul 11
042Dual-Gate Evidence Rails for Attested Agentic AI: Deny-Before-Inference and Permit-Before-Commit Control of External EffectsOpenAlexPaperY N LeeJul 11
043Community-Driven Security for AI Agents: Evolution of an Adversarial Testing FrameworkOpenAlexPaperMichael K. SalemeJul 10
044Community-Driven Security for AI Agents: Evolution of an Adversarial Testing FrameworkOpenAlexPaperMichael SalemeJul 10
045Contextual Bleed: A Conceptual Framework and Pre-Empirical Protocol Specification for Tool-Routing Integrity in Instruction-Tuned Language ModelsOpenAlexPaperE. KatzJul 9
046Contextual Bleed: A Conceptual Framework and Pre-Empirical Protocol Specification for Tool-Routing Integrity in Instruction-Tuned Language ModelsOpenAlexPaperE. KatzJul 9
047EmbedGuard: Cross-Layer Detection and Provenance Attestation for Adversarial Embedding Attacks in RAG SystemsOpenAlexPaperNeeraj Kumar Singh BeshaneJul 9
048EmbedGuard: Cross-Layer Detection and Provenance Attestation for Adversarial Embedding Attacks in RAG SystemsOpenAlexPaperBeshane, Neeraj Kumar SinghJul 9
049The XREALISM® PREDECISION™ Core: A Protected FPGA Hardware Architecture for Pre-Decision StabilizationOpenAlexPaperLadgrad Ladislav GradečakJul 9
050The XREALISM® PREDECISION™ Core: A Protected FPGA Hardware Architecture for Pre-Decision StabilizationOpenAlexPaperLadgrad Ladislav GradečakJul 9
051SAE-v1.0: Sovereign AI Execution Standard - Deterministic Governance for Autonomous AI.OpenAlexPaperMushtaque Ahmed RajputJul 8
052SAE-v1.0: Sovereign AI Execution Standard - Deterministic Governance for Autonomous AI.OpenAlexPaperMushtaque Ahmed RajputJul 8
053Reflective Umbrella: Deflecting Prompt Injections in Cloud-Based Large Language Models using Integrated Legal Rules.OpenAlexPaperBanujan VijayarajanJul 7
054Reflective Umbrella: Deflecting Prompt Injections in Cloud-Based Large Language Models using Integrated Legal Rules.OpenAlexPaperBanujan VijayarajanJul 7
055[SUPERSEDED] Calibration Poisoning, Not Erasure: Substrate Honesty Probes Survive Knowledge-Preserving Weight Attacks When the Auditor's Calibration Is PrivateOpenAlexPaperAlexander RodabaughJul 7
056[SUPERSEDED] Calibration Poisoning, Not Erasure: Substrate Honesty Probes Survive Knowledge-Preserving Weight Attacks When the Auditor's Calibration Is PrivateOpenAlexPaperAlexander RodabaughJul 7
057Supply Chain Attacks on ML Models: Poisoning, Backdoors, and Trojan Detection in Open WeightsOpenAlexPaperОлег Ивченко, Iryna IvchenkoJul 6
058Supply Chain Attacks on ML Models: Poisoning, Backdoors, and Trojan Detection in Open WeightsOpenAlexPaperОлег Ивченко, Iryna IvchenkoJul 6
059Supply Chain Attacks on ML Models: Poisoning, Backdoors, and Trojan Detection in Open WeightsOpenAlexPaperОлег Ивченко, Iryna IvchenkoJul 6
060Supply Chain Attacks on ML Models: Poisoning, Backdoors, and Trojan Detection in Open WeightsOpenAlexPaperОлег Ивченко, Iryna IvchenkoJul 6

Showing 60 of 1,355 documents · scroll for more