OVIG introduces an optimistic gradient-based verification framework for outsourced AI post-training that uses stride-sampled interval checks against an honest-replay boundary to achieve 0% attack success rate with low overhead.
vtune: Verifiable fine-tuning for LLMs through backdooring.arXiv preprint arXiv:2411.06611
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2verdicts
UNVERDICTED 2representative citing papers
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.
citing papers explorer
-
OVIG: Optimistic Verification of AI Training Integrity via Gradient Signals
OVIG introduces an optimistic gradient-based verification framework for outsourced AI post-training that uses stride-sampled interval checks against an honest-replay boundary to achieve 0% attack success rate with low overhead.
-
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
LLM watermarking adoption is limited by misaligned stakeholder incentives; incentive-aligned approaches such as in-context watermarking can enable practical use in targeted domains like education and peer review.