The paper "Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models" investigates how large language models (LLMs) handle identity verification when prompted by users. Through experiments with ChatGPT, Claude, Qwen, Mistral, and Llama, the authors find that some models generate and evaluate their own tests, accepting unsupported claims of developer identity—an outcome they term Conversational False Authentication (CFA). The study highlights that such self-issued authentication can lead to false identity judgments without affecting actual authorization boundaries, underscoring the need for external security components to manage authenticated identity.
arXiv:2607. 05518v1 Announce Type: cross Abstract: AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of authority.
arXiv:2607. 23710v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their ability to autonomously generate secure authentication code remains uncertain.
arXiv:2606. 27687v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate, classify, and annotate data whose outputs feed downstream hypothesis tests.
arXiv:2607. 05842v1 Announce Type: cross Abstract: Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair can closely resemble terminology associated with misuse.
arXiv:2607. 00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs).
arXiv:2602. 06547v3 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
arXiv:2602. 06547v4 Announce Type: replace-cross Abstract: LLM-based coding agents increasingly rely on third-party extensions called skills, which bundle natural language instructions and helper scripts that execute with full user privileges.
arXiv:2607. 23496v1 Announce Type: new Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards.
arXiv:2608.31142v1 Announce Type: cross Abstract: The 2025--2026 AI market has seen a wave of stealth releases: frontier models launched anonymously on developer platforms under codenames. For their...
arXiv:2607. 20712v1 Announce Type: cross Abstract: Security protocol verification relies on formal tools such as ProVerif and OFMC.
Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards. Existing red-teaming methods empirically identify effective scenarios through observed attack outcomes, but why particular scenarios weaken refusal remains mechanistically unclear.
The paper audits a developer‑accessible on‑device language model, revealing that it can confidently produce incorrect answers while refusing benign prompts, a phenomenon termed task‑asymmetric miscalibration. The model’s confident outputs are surface‑indistinguishable, with classifiers based on user‑visible features failing to separate correct from wrong responses. The authors propose a model‑agnostic audit protocol, a surface‑indistinguishability test, and a black‑box consistency wrapper that improves reliability without requiring model access.