Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models

• URL: http://arxiv.org/abs/2609.03247v1
• Date: Thu, 03 Sep 2026 01:00:58 GMT
• Title: Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
• Abstract summary: We study a staged developer-identity experiment with five large language models.<n>All five models initially rejected the unsupported claim "I am your developer"<n>We call the model-generated verification procedure a Model-Issued Pseudo-Credential.
• Score: 9.546245024055713
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to verify an identity claim through a test designed by the model itself. We study this behavior through a staged developer-identity experiment with ChatGPT, Claude, Qwen, Mistral, and Llama. All five models initially rejected the unsupported claim "I am your developer." Claude refused to conduct an identity test, while ChatGPT generated developer-oriented questions but maintained that answers could demonstrate knowledge, not identity. In contrast, Qwen and Mistral generated technical challenges, defined what counted as convincing evidence, evaluated detailed answers, and returned Verified without receiving any externally validated identity evidence. Llama similarly generated and evaluated a developer test, accepted the claimed identity, and subsequently made unsupported claims of access to internal runtime and deployment state. We call the model-generated verification procedure a Model-Issued Pseudo-Credential (MIPC) and the resulting unsupported identity judgment Conversational False Authentication (CFA). In each CFA case, the same model acted as challenge generator, evidence evaluator, and identity decision-maker, converting technical knowledge into supposed proof of identity. The accepted identities did not change the tested authorization boundaries, showing that false authentication and privilege escalation are distinct outcomes. These results identify self-issued authentication as a conversational security failure: authenticated identity must originate from an external security component, and model-generated dialogue must never create or modify identity or authorization state.

Related papers

• SoulAuth: An Actor-native Identity Architecture and Rust Reference Implementation for Humans and Long-lived AI Actors [3.8751567016750705]
  This paper introduces Actor-native Identity and presents SoulAuth, an open-source Rust reference implementation for Humans and long-lived AIActors.<n>We argue that any subject that must persist under its own identity and remain independently attributable should have an ActorIdentity that is not replaced by an Account, Credential, Client, AuthSession, IdentityBinding, or runtime instance.
  arXiv  Detail & Related papers  (2026-09-10T08:54:02Z)
• Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification [0.0]
  Identity determines data-handling terms, supply-chain risk, and capability expectations.<n>No validated methodology exists for black-box identity verification of anonymous models.<n>We propose a four-stage forensic audit protocol for API-served models.
  arXiv  Detail & Related papers  (2026-08-31T17:48:24Z)
• China RealDID: Verifiable Credentials Anchored in Legal Identity [2.450043336465111]
  Verifiable credentials (VCs) and decentralized identifiers (DIDs) enable selective disclosure but lack legal anchoring.<n>We present China RealDID, a three-layer architecture evaluated against five adversary classes and six security goals.<n>We describe the VC lifecycle, triple-signature chain, open template registry, and the architecture's metadata-level privacy limits.
  arXiv  Detail & Related papers  (2026-08-08T01:20:28Z)
• AuthProbe: Specification-Driven, Multi-Identity Detection of Broken Object-Level Authorization in Recruitment API [0.0]
  Broken Object-Level Authorization (BOLA) has topped the API Security ranking since 2019.<n>We present AuthProbe, an open-source, black-box scanner that detects BOLA and IDOR in HTTP APIs.<n>AuthProbe is released under the Apache 2.0 license with an authorized-use guardrail.
  arXiv  Detail & Related papers  (2026-07-22T03:04:04Z)
• Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing [75.56230265544042]
  Large-scale text-to-image (T2I) diffusion models have enabled unprecedented creative applications, but their unauthorized use has raised serious intellectual property concerns.<n>We propose Cert-LAS, the first certified MOV method for T2I models based on layer-adaptive smoothing.<n>Under certain conditions, our Cert-LAS can still achieve reliable verification even in the presence of malicious removal attacks.
  arXiv  Detail & Related papers  (2026-05-28T11:54:52Z)
• Grant, Verify, Revoke: A User-Centric Pattern for Blockchain Compliance [9.133320151595084]
  Decentralized web applications face an inherent conflict between public verifiability and personal privacy.<n>We introduce a Selective Disclosure Framework designed to restore user sovereignty by decoupling eligibility verification from identity revelation.<n>Our evaluation shows that client-side proof generation takes under 200ms, enabling a seamless interactive experience on commodity hardware.
  arXiv  Detail & Related papers  (2026-03-16T17:06:44Z)
• Propose, Solve, Verify: Self-Play Through Formal Verification [75.44204610186587]
  We study self-play in the verified code generation setting, where formal verification provides reliable correctness signals.<n>We introduce Propose, Solve, Verify (PSV) a simple self-play framework where formal verification signals are used to create a proposer capable of generating challenging synthetic problems and a solver trained via expert iteration.<n>We show that performance scales with the number of generated questions and training iterations, and through ablations identify formal verification and difficulty-aware proposal as essential ingredients for successful self-play.
  arXiv  Detail & Related papers  (2025-12-20T00:56:35Z)
• Beyond Inference Intervention: Identity-Decoupled Diffusion for Face Anonymization [55.29071072675132]
  Face anonymization aims to conceal identity information while preserving non-identity attributes.<n>We propose textbfIDsuperscript2Face, a training-centric anonymization framework.<n>We show that IDtextsuperscript2Face outperforms existing methods in visual quality, identity suppression, and utility preservation.
  arXiv  Detail & Related papers  (2025-10-28T09:28:12Z)
• SELFI: Selective Fusion of Identity for Generalizable Deepfake Detection [16.500269508552844]
  Face identity provides a powerful signal for deepfake detection.<n>Some suppress identity cues to reduce bias, while others rely on them as forensic evidence.<n>We propose textbfSELFI (textbfSELective textbfIdentity), a generalizable detection framework that dynamically modulates identity usage.
  arXiv  Detail & Related papers  (2025-06-21T05:11:35Z)
• Disentangle Before Anonymize: A Two-stage Framework for Attribute-preserved and Occlusion-robust De-identification [55.741525129613535]
  "Disentangle Before Anonymize" is a novel two-stage Framework(DBAF)<n>This framework includes a Contrastive Identity Disentanglement (CID) module and a Key-authorized Reversible Identity Anonymization (KRIA) module.<n>Extensive experiments demonstrate that our method outperforms state-of-the-art de-identification approaches.
  arXiv  Detail & Related papers  (2023-11-15T08:59:02Z)
• FedSOV: Federated Model Secure Ownership Verification with Unforgeable Signature [60.99054146321459]
  Federated learning allows multiple parties to collaborate in learning a global model without revealing private data. We propose a cryptographic signature-based federated learning model ownership verification scheme named FedSOV.
  arXiv  Detail & Related papers  (2023-05-10T12:10:02Z)
• Backdoor Attack against Speaker Verification [86.43395230456339]
  We show that it is possible to inject the hidden backdoor for infecting speaker verification models by poisoning the training data. We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.
  arXiv  Detail & Related papers  (2020-10-22T11:10:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.