{"data":{"id":"2902289c-0189-4006-9f17-4400d028f9dc","title":"Text Adversarial Attacks With Dynamic Outputs","summary":"Researchers introduce the Textual Dynamic Outputs Attack (TDOA), a text adversarial attack for settings where the number and content of model labels vary, such as LLM outputs and multi-label classification. TDOA trains a clustering-based surrogate model that approximates dynamic fine-grained outputs with static coarse-grained labels, and uses a farthest-label targeted strategy to induce larger output changes. Evaluated on five datasets and ten victim models including GPT-4o and GPT-4.1, it reaches an 80.8% maximum attack success rate with five queries per text.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11653428","publishedAt":"2026-08-12T13:16:39.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["GPT-4o","GPT-4.1"],"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":"2026-08-12T13:16:39.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":null}}