Integrity

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 26

All topics

Certified Multi-Source Integrity for Structured Agent Actions
Sep 28, 2026Anmol Pandey, Aditya Jain, Liang Chen +2Integrity On-Chain Attestations
University of Warwick · University of Hertfordshire
Integrity Detection and Characterization of Malicious Injections in RAVEN II
Sep 27, 2026Xingli Zhang, Diba Afroze, Fei Hu +1Surgical Robots Instruction Injection Attacks
School of Computing and Informatics University of Louisiana at Lafayette Lafayette, USA · Department of Electrical and Computer Engineering University of Alabama Tuscaloosa, USA
MutMem-V2: Cryptographically Authorized Mutation in Persistent Agent Memory Portable Verification and Reproducible Evidence
Sep 1, 2026Walid SaidiOn-Chain Attestations Nativemem
Independent researcher
A Mathematical Framework for Legacy, Governance, and Decision Integrity in Enterprise AI
Sep 1, 2026Shorab SarkerArtificial Intelligence Governance Governance
Independent Researcher · The Math Behind Innovation
Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap
Aug 30, 2026Ashok Subbabhatta GopalakrishnaZero-Knowledge Proofs On-Chain Attestations
independent researcher
Where Is the Cost of Third-Party API Routers in Agentic Software Development?
Jul 26, 2026Donghao Fu, Jingxin Li, Xue Jiang +1Coding Agents Agentic Deployments
School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · School of Software, Beihang University, Beijing, China · School of Computer Science, Peking University, Beijing, China
Dynamic Capability Scoping for Enterprise AI Agents: A Synthetic Dataset and Three-Source Permission Architecture
Jul 24, 2026Halil Burak NoyanIntegrity Synthetic Data
Independent Researcher, London, United Kingdom.
Integrity of peer-to-peer distributed LLM inference under malicious nodes
Jul 21, 2026Mert Cihangiroglu, Antonino NoceraPeer-To-Peer Large Language Model Reliability
DCALab, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Italy
Agent-Safety Evaluations as Load-Bearing Evidence: A Vendor-Neutral, Cross-Harness Reconstructability Metric
Jul 14, 2026Oleg SolozobovAgentic Evaluations Integrity
Independent Researcher (Global)
Value of Information under Imprecise Probabilities: Decision-Rule-Specific Values and Fixed-Measure Envelopes on a Credal Set
Jun 26, 2026Rowan IskandarConditional-Value-At-Risk Minimax
Medtronic Trading Sàrl, Tolochenaz, VD, Switzerland · Center for Evidence Synthesis in Health, Brown University School of Public Health, Providence, RI, USA
Deterministic Integrity Gates for LLM-Assisted Clinical Manuscript Preparation: An Auditable Biomedical Informatics Architecture
Jun 8, 2026Yoojin Nam, Jinhoon Jeong, Namkug KimLarge Language Model Reliability Integrity
Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea · Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea · Aperivue, Incheon, Republic of Korea +2
Ciphera: A Decentralised Biometric Identity Framework
May 28, 2026Ankit Kanaiyalal Prajapati, Shahzad Memon, Mohammed Mahir Rahman +1Biometrics Integrity
Department of Computer Science and Digital Technologies University of East London
QML-PipeGuard: Drift-Aware Behavioral Fingerprinting for Quantum Machine Learning Pipeline Integrity
May 24, 2026Esra YeniarasQuantum Machine Learning Integrity
Quantum Security and Post-Quantum Cryptography Researcher (previously Assistant Professor in Cyber Security at Copenhagen School of Business (EK))
DART: Semantic Recoverability for Structured Tool Agents
May 22, 2026Ke Yang, Panpan Li, Zonghan Wu +3Rollback Intermediate Checkpoints
1MOS Intelligent Connectivity Technology Co. Ltd. · 2Sichuan Vocational College of Post and Telecom · 3East China Normal University +2
MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation
May 20, 2026Ahanaf Hasan AriqPac-Bayesian Theory Empirical Risk Minimization
Ideal School and College
ContractBench: Can LLM Agents Preserve Observation Contracts?
May 17, 2026Jicheng Wang, Yifeng He, Zili Wang +3Contracts Large Language Model Agents
University of California, Davis · University of Southern California · University of Hong Kong
A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web
May 10, 2026Shusaku Egami, Masahiro HamasakiGenerative Artificial Intelligence Trustworthy Artificial Intelligence
National Institute of Advanced Industrial Sciencen and Technology (AIST) · Koto, Tokyo, Japan
When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
May 4, 2026Mingyu Luo, Zihan Zhang, Zesen Liu +7Attacker Large Language Model Large Language Model Agents
Fudan University, Shanghai, China · The Hong Kong University of Science and Technology, Hong Kong, China · Huazhong University of Science and Technology, Wuhan, China
Tatemae: Detecting Alignment Faking via Tool Selection in LLMs
Apr 29, 2026Matteo Leonesi, Francesco Belardinelli, Flavio Corradini +1Deception Model Vulnerabilities
Department of Computing Imperial College London
Proof of Execution: Runtime Verification for Governed AI Agent Actions
Apr 26, 2026James Rhodes, George KangRuntime Enforcement Integrity
AlphaBitCore, Inc.
Structural Enforcement of Goal Integrity in AI Agents via Separation-of-Powers Architecture
Apr 26, 2026Rong XiangArtificial Intelligence Alignment Authorization
Reconstructive Authority Model: Runtime Execution Validity Under Partial Observability
Apr 24, 2026Marcelo Fernandez - TraslaIAOn-Chain Attestations Runtime Enforcement
Independent Research
Quantification of Credal Uncertainty: A Distance-Based Approach
Mar 28, 2026Xabier Gonzalez-Garcia, Siu Lun Chau, Julian Rodemann +6Uncertainty Multiclass Classification
Dept. of Statistics, CS & Mathematics, Public Univ. of Navarre · EPIC Lab, Nanyang Technological Univ. Singapore · Rational Intelligence Lab, CISPA Helmholtz Center for Information Security +7
Incentive Aware AI Regulations: A Credal Characterisation
Mar 5, 2026Anurag Singh, Julian Rodemann, Rajeev Verma +2Regulation Artificial Intelligence Governance
1Rational Intelligence Lab, CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Department of Statistics, LMU Munich, Germany · 3UvA-Bosch Delta Lab, University of Amsterdam, Netherlands +1
The Journal of Prompt-Engineered (Moral) Philosophy Or: Why AI-Assisted Ethics Research Requires Process Transparency
Nov 10, 2025Michele LoiTransparency Ethics
University of Milan
Optimal Conformal Prediction under Epistemic Uncertainty
May 25, 2025Alireza Javanmardi, Soroush H. Zargarbashi, Santo M. A. R. Thies +3Online Conformal Prediction Predictive Uncertainty
1LMU Munich · 2MCML · 3CISPA +3

Sep 28, 2026, cs.CRJ/K move · Enter open · S save

Certified Multi-Source Integrity for Structured Agent Actions

Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple+1

University of Warwick · University of Hertfordshire

Integrity On-Chain Attestations Adversarial Corruption Large Language Model Agents Fraud Detection

Open paper AskPDF arXiv

LLM agents increasingly take privileged, often irreversible structured actions, such as paying an invoice. They assemble each action from action-critical fields in documents and tool outputs that an adversary can corrupt, and indirect prompt injection can drive the model itself to extract attacker-chosen values. Current defenses gate on a source's trust label or certify free-text answer quality. None certifies the integrity of a coupled, policy-bound structured action under a corruption budget that accounts for shared upstream sources. We characterize when such an action is safely certifiable and give the maximally live safe certifier. It admits an action only when each field clears the rule its evidence structure supports: a bounded corruption radius over corruption-distinct evidence classes, counted by a minimum hitting set so that re-publishing or laundered copies cannot manufacture a quorum, deterministic reconciliation for complementary fields, and a trusted anchor where the evidence leaves a field single-sourced. We formalize two robustness notions, validate each mechanism by ablation, and measure how often the multi-source precondition holds on sanctions designations (70,966 entities) and software supply-chain provenance (450 packages). Under upper-bound proxies, genuine corroboration is a minority phenomenon in both, and naive attestation counting overstates it, since witnesses that look independent collapse to two corruption-distinct domains once shared origin is counted. Across five current models in a real agent loop, a realistic injection fools every model but one and a naive agent then executes the fraudulent action on most attacks. The certifier admits no unsafe action and recovers the correct value where corroboration permits, while action-gating and provenance baselines are broken in every world of our harness by some attack in its space.

Momentum

Related topics

Latest papers 26