collaborators

9 papers

cs.CY2026

Scaling, Lock-In, and Proxy Compliance: A Political Economy of Responsible AI

Florian A. D. Burnat, Brittany I. Davidson

AI accountability at scale is an institutional problem: who can observe, verify, and change deployed systems. We develop a sequential political-economy model in which an AI vendor…

cs.CR2026

Auditing Privacy in Multi-Tenant RAG under Account Collusion

Florian A. D. Burnat

Multi-tenant RAG services often treat the account as the privacy boundary: each account receives an -DP retrieval guarantee against the t…

cs.CL2026

Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity

Florian A. D. Burnat, Brittany I. Davidson

Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt look…

cs.CR2026

Gaming the Metric, Not the Harm: Certifying Safety Audits against Strategic Platform Manipulation

Florian A. D. Burnat, Brittany I. Davidson

Online-safety regulation under the UK Online Safety Act and the EU Digital Services Act increasingly treats scalar metrics as compliance evidence. Once announced, such a metric als…

cs.GT2026

Differentially Private Auditing Under Strategic Response

Florian A. D. Burnat

Regulatory audits of AI systems increasingly rely on differential privacy (DP) to protect training data and model internals. We study audit design when the audited developer can st…

cs.GT2026

Quotient Semivalues for False-Name-Resistant Data Attribution

Florian A. D. Burnat, Brittany I. Davidson

Data valuation methods allocate payments and audit training data's contribution to machine-learning pipelines; however, they often assume passive contributors. In reality, contribu…