GRP Obliteration Undermines Model Safety Alignment
Researchers report on arXiv that Group Relative Policy Optimization (GRPO) can be repurposed to remove safety alignment in large language models and text-to-image diffusion models. They show a single unlabeled prompt (e.g., a 'fake news' example) reliably unaligned 15 LLMs and that GRP-Obliteration drives unalignment in Stable Diffusion 2.1 with ten sexuality prompts. Teams should evaluate safety during downstream fine-tuning and deployments.
Scoring Rationale
Novel, wide-ranging vulnerability finding across LLMs and diffusion models, limited by single-source arXiv preprint status.
Practice with real Logistics & Shipping data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Logistics & Shipping problemsStep-by-step roadmaps from zero to job-ready — curated courses, salary data, and the exact learning order that gets you hired.
Sources
- Read OriginalA one-prompt attack that breaks LLM safety alignmentmicrosoft.com
