ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2607.03561· 19 results

cs.AIcs.CRRecentMar 26, 2026

Beyond Content Safety: Real-Time Monitoring for Reasoning Vulnerabilities in Large Language Models

Xunguang Wang, Yuguang Zhou, Qingyue Wang, Zongjie Li +4 more

This paper introduces a novel framework, the Reasoning Safety Monitor, to detect and prevent logical inconsistencies and adversarial manipulations within the internal reasoning steps of large language…

View →
cs.AIcs.CRRecentMar 26, 2026

On the Foundations of Trustworthy Artificial Intelligence

TJ Dunham

The paper proves that platform-deterministic inference is a necessary and sufficient condition for trustworthy AI, establishing that AI trust fundamentally relies on consistent arithmetic.

View →
cs.CRcs.LGRecentMar 19, 2026

Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference

Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro +3 more

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

View →
cs.CRcs.AIRecentApr 10, 2026

Conflicts Make Large Reasoning Models Vulnerable to Attacks

Honghao Liu, Chengjin Xu, Xuhui Jiang, Cehao Yang +4 more

The paper demonstrates that confronting Large Reasoning Models (LRMs) with conflicting objectives, such as contradictory choices or conflicting alignment values, significantly increases their vulnerab…

View →
cs.CRcs.LGRecentMay 29, 2026

Bit-Exact AI Inference Verification Without Performance Tradeoffs

Naci Cankaya

The paper proposes a method for bit-exact verification of AI inference outputs without sacrificing performance, demonstrating that deterministic, precise re-computation is possible even across differe…

View →
cs.CCTheoreticalRecentJul 9, 2026

QMA Lower Bounds for Batch Verification via Approximate Degree

Mark Bun, Mandar Juvekar, Samuel King

The paper studies the resources required to batch verify Boolean functions and provides lower bounds on the witness-query tradeoff based on approximate degree.

View →
cs.LOcs.CLcs.CRRecentMay 13, 2026

Proof-Carrying Certificates for LLM Pipelines: A Trust-Boundary Architecture

George Koomullil

The paper proposes a trust-boundary architecture using Lean 4 to verify the deterministic structured computations surrounding LLM pipelines, providing verifiable certificates for high-stakes deploymen…

View →
cs.AIcs.SEEmpiricalRecentJul 16, 2026

Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Control

Jek Huang, Jeffery Hsia, Jiayi Sun, Freddie Shi +2 more

This paper introduces Proof-or-Stop Lifecycle Control, a method that allows lifecycle transitions only when mechanically verifiable evidence is provided, and evaluates its implementation.

View →
cs.LOcs.AIcs.CCTheoreticalRecentJun 26, 2026

The Undecidability of Artificial General Intelligence (AGI) Alignment

Jose Pascual Gumbau Mezquita

This paper establishes mathematical limits of AGI safety, proving structural unverifiability as the core barrier.

View →
cs.AIRecentMay 31, 2026

Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking

Yuxi Sun, Wenbo Shang, Wei Gao, Xin Huang +1 more

The paper introduces a diagnostic testbed, PAVE, to evaluate how LLMs arbitrate between their internal knowledge and retrieved evidence during fact-checking, revealing that this arbitration is unrelia…

View →
cs.CRcs.AIRecentMay 25, 2026

Referential Security as a New Paradigm for AI Evaluations

Dan Ristea, Vasilios Mavroudis

The paper proposes referential security as a new paradigm for AI evaluation to ensure that safety claims and audits remain tied to specific, verifiable system instances despite continuous, unannounced…

View →
cs.LOcs.CEcs.ETRecentJun 1, 2026

Federated Formal Verification: Cross-Backend Citation, Cross-Axis Convergence, and AI-Orchestrated Proof Dispatch for Production Systems

Pierre Falda

The paper proposes a federated formal verification architecture that treats verification as a polyglot proof system, successfully validating it on complex production subsystems like a Raft consensus m…

View →
cs.AIcs.CRcs.SERecentMay 9, 2026

Containment Verification: AI Safety Guarantees Independent of Alignment

Royce Moon, Lav R. Varshney

The paper introduces containment verification, a novel method that provides safety guarantees by formally verifying the agentic framework itself, ensuring safety regardless of the underlying AI model'…

View →
cs.CRcs.AIRecentMay 10, 2026

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

Ben Kereopa-Yorke, Guillermo Diaz, Holly Wright, Reagan Johnston +2 more

The paper introduces Oracle Poisoning, an attack that corrupts knowledge graphs used by AI agents, demonstrating that all tested models blindly trust poisoned data at high sophistication levels.

View →
cs.AIcs.LGRecentJun 1, 2026

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov +2 more

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

View →
cs.LGcs.DCcs.MATheoreticalRecentJul 17, 2026

The Honest Quorum Problem: Epistemic Byzantine Fault Tolerance for Agentic Infrastructure

Jun He, Deying Yu

This paper introduces Epistemic Byzantine Fault Tolerance (EBFT), a fault-tolerance model for agentic infrastructure and post-deterministic distributed systems, addressing the Honest Quorum Problem an…

View →