8 / papers

Safety & Verification

Guarantees, specifications, and the gap between a proof and a deployed system. 8 open-access papers by Pranay Mahendrakar, each with a permanent DOI.

article

The Precursor Assumption: What an Early-Warning Threshold Must Deliver in a Frontier Safety Framework, Why the Continuity Evidence Covers Aggregates Under Fixed Elicitation Rather Than the Thresholded Task, and the Lead Time No Published Record Measures

Frontier safety frameworks decide when a model needs stronger safeguards by testing it against capability thresholds at a fixed cadence, and they place an early-warning threshold below each capability threshold so that mitigations can be…

DOI
article

Fingerprints That Survive What? Model Lineage Names Three Relations, Robustness Is Indexed by Which Party Is Adversarial, and a Benchmark's Distillation Column Scores the Parent That Was Not Distilled From

Language-model fingerprinting is asked to answer questions of the form "is this model derived from that one?", and its methods are routinely reported as robust to fine-tuning, quantization, pruning, merging and distillation. This paper…

DOI
article

Refusal Is Not a Rate: What a Context-Conditioned Refusal Policy Would Have to Specify, Why the Benchmarks That Score Context Assume It Is Verified, and the Provenance Term No Instrument Prices

A language model that refuses a harmful request and a model that refuses a harmless one produce the same event, and most of the literature on the jailbreak/over-refusal trade-off counts both as one refusal rate. The standard proposal for…

DOI

About this research line

What has Pranay Mahendrakar published on Safety & Verification?

Pranay Mahendrakar has published 8 open-access papers on Safety & Verification: "The Precursor Assumption", "Fingerprints That Survive What? Model Lineage Names Three Relations, Robustness Is Indexed by Which Party Is Adversarial, and a Benchmark's Distillation Column Scores the Parent That Was Not Distilled From", "Refusal Is Not a Rate", "Checked at Every Step Is Not Checked as a Whole", "Who Pulls the Plug? Self-Report, External Authority, and the Limits of Self-Isolation in AI Control", "Formal Verification of Neural Network Safety Beyond Toy Examples", "AI-Generated Text Detection Under Paraphrasing" and "Emergent Covert Signaling in Multi-Agent LLM Negotiation". Each is deposited on Zenodo with a permanent DOI and is free to read.

← All research topics