{"data":{"id":"7bd4553f-caae-4e29-adac-18378182d73f","title":"From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion","summary":"Researchers present STIA, a Speech Token Inversion Attack that generates speech with attacker-specified text in a victim's voice from a single short leaked speech representation. The attack needs neither the original audio nor its transcript. A conditional flow-matching model, trained on same-speaker utterance pairs from public speech datasets, combines the leaked speaker characteristics with the target text. With a Moshi representation leak corresponding to 3 seconds of speech, STIA reaches an average CAM++ speaker cosine similarity of 0.78 and a target-text word error rate of 3.80%.","solution":"N/A -- no mitigation discussed in source.","labels":["research","privacy"],"sourceUrl":"https://arxiv.org/abs/2610.34688v1","publishedAt":"2026-10-26T01:24:54.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["pii_leakage","other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Moshi"],"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":"2026-10-26T01:24:54.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality"],"aiComponentTargeted":"inference","llmSpecific":false,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}