{"data":{"id":"42034c07-c3db-4712-8aaa-ff50a685152e","title":"Apple Intelligence AI Guardrails Bypassed in New Attack","summary":"RSAC researchers bypassed the guardrails of Apple Intelligence using the Neural Exect method and Unicode manipulation. The source text gives no further detail on the attack's mechanics or impact.","solution":"N/A -- no mitigation discussed in source.","labels":["security","safety"],"sourceUrl":"https://www.securityweek.com/apple-intelligence-ai-guardrails-bypassed-in-new-attack/","publishedAt":"2026-04-09T13:43:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"medium","attackType":["jailbreak"],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Apple"],"affectedVendorsRaw":["Apple Intelligence"],"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":"2026-04-09T13:43:07.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":["AML.T0054"]}}