{"data":{"id":"b5f519ea-1a01-45da-9ac7-148568febe93","title":"A Layer-wise Study of How Style Rewriting Breaks the Calibration of Zero-Shot LLM Fake-News Detectors","summary":"A layer-wise study tests how style rewriting affects the confidence of zero-shot LLM fake-news detectors. Across LLaMA-3-8B, Qwen2.5-7B and Mistral-7B on three benchmarks, rewriting articles into sensational or emotionally charged styles, without changing facts, makes the models markedly less accurate, worse than random guessing under the strongest attack, while their confidence stays the same. The authors conclude that an LLM's confidence about veracity cannot be trusted as a safety signal when an article's style may have been manipulated.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.11239v1","publishedAt":"2026-11-08T08:48:36.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion","jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLaMA-3-8B","Qwen2.5-7B","Mistral-7B"],"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":"2026-11-08T08:48:36.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}