{"data":{"id":"4b709985-f45f-471e-bc96-3d10ecb57e46","title":"PromptFishing: Active Hallucination Inducement to Distinguish LLMs From Humans","summary":"Researchers propose PromptFishing, an active method for identifying LLM-driven social accounts by embedding machine-readable prompts in ordinary topics that induce a target hallucinated response. The method uses a gradient-guided two-stage beam search to generate adversarial suffixes, first pushing responses off topic and then aligning them with the target. On Twitter data, it reports a true positive rate above 0.85 with a false positive rate below 0.01.","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"http://ieeexplore.ieee.org/document/11592605","publishedAt":"2026-07-01T13:17:24.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-07-01T13:17:24.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":"peer_reviewed","atlasIds":null}}