{"data":{"id":"cd3ab41f-aefe-4879-9b0b-a7fcc8274826","title":"Steering Gemini using BIDPO vectors","summary":"Alex Turner and Mark Kurzeja tested BIDPO-trained steering vectors on Gemini 1.5v1 Flash and Pro, where they raised TruthfulQA scores by more than 10% while mostly retaining capabilities. After Gemini 1.5v2 arrived, prompt-based steering baselines became significantly stronger, and BIDPO did not beat them, which ended the project.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://deepmindsafetyresearch.medium.com/steering-gemini-using-bidpo-vectors-8a0e7e1da1c9?source=rss-55e08ddea42e------2","publishedAt":"2025-01-31T02:03:37.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Gemini 1.5 Flash","Gemini 1.5 Pro","Gemini 1.5v2"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2025-01-31T02:03:37.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"industry","atlasIds":null}}