FedTrust-CVDv2 is presented, a federated coordinated vulnerability disclosure framework that separates evidence validation, interorganizational coordination, human governance, human governance, and permissioned auditing from evidence validation, interorganizational coordination, and permissioned auditing.
Abstract
AI-assisted vulnerability discovery can produce technically plausible findings faster than maintainers can validate, coordinate, and safely disclose them. The resulting challenge is not only to establish whether a vulnerability claim is credible, but also to ensure that its supporting evidence, human authorization, intended recipients, and applicable policy remain bound to the same case revision. We present FedTrust-CVDv2, a federated coordinated vulnerability disclosure framework that separates evidence validation, interorganizational coordination, human governance, and permissioned auditing. The framework binds independently signed observations to exact evidence revisions and scopes external actions to approved payloads, audiences, expiry, policy, and revocation state while preserving existing CVE Numbering Authority (CNA) roles. A local reference implementation accepted all 25 valid fixtures and rejected all 650 invalid fixtures across 27 constructed policy families; six single-safeguard ablations admitted 25-75 invalid fixtures. Supporting experiments exercised signed messaging, authenticated encryption, audit certificates, and finite quorum-set conditions. A PHP2Shell case formulation illustrates how runtime evidence, patch state, emergency coordination, and CNA authority can be represented without attributing unsupported claims to AI or treating audit integrity as vulnerability truth. This short version focuses on the architecture, evidence-to-action contract, selected conformance results, and case formulation. An expanded version containing the full implementation, extended experiments, operational analysis, and additional results will be submitted to a journal.
This work develops Publication Authority as an exact-state, non-transferable, single-use publication capability and instantiate it in PAC-2026 (Publication-Accountability Calculus), a machine-readable AIJIM Protocol candidate, and evaluates its fourth bounded semantic freeze (SF-4), a fixed-profile specification design...
Torsten Tiltack, Yi-Fei Dong, Kun Yu et al.· 0 citations
Cheating and other threats to score integrity have long challenged language testing, and concerns have intensified with remote proctoring and generative artificial intelligence. Yet prevailing validity frameworks treat test security primarily as an operational matter rather than as a component of validity. We argue tha...
Ramsey L. Cardwell, Daniel R. Isbell, Jieun Kim et al.· Language Testing· 0 citations
VeriWeave Govern is presented, a deterministic runtime governance layer that evaluates structured agent actions against versioned policies, validates typed evidence, applies fixed deny>review>allow precedence, routes consequential actions to accountable human review, and records replayable tamper-evident audit state.
Kabeh Mohsenzadegan, V. Tavakkoli, K. Kyamakya· 0 citations
: Large language model (LLM)-based phishing detectors can produce decisions and explanations, but adversarial webpages violate the assumption that all input text is trustworthy evidence. Hidden comments, metadata, scripts, Cascading Style Sheets (CSS), and retrieved snippets can act as instruction-injection channels, w...
Yue-Kui Xu, Xiong-Zhang Luo· Computers, Materials & C...· 1 citation
This paper argues that AI-native academia should build a Community Verification Layer: interoperable, policy-governed infrastructure that converts researchers'routine reading and checking into persistent, claim- and version-linked evidence, while routing scarce deeper verification toward uncertain, consequential, and n...
A correctly governed LLM agent can reach a state in which neither continuing execution nor automatically halting is admissible: the system has detected a persistent failure of its observability or drift-detection layer, but cannot itself decide who has the authority to resume, deny, or recalibrate the deployment. We ca...
Marcelo Fernandez· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.