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%.

Related items

• MediumCVE-2026-116575: Mem0 SDK session scope collision in add() exposes cross-tenant conversationsSimilar attack · NVD/CVE Database
• HighCVE-2026-115924: Rembg unauthenticated file disclosure through public /api/remove endpointSimilar attack · NVD/CVE Database
• HighCVE-2026-115915: vLLM image loading flaw allows EPS payload dispatchSimilar attack · NVD/CVE Database
• LowThe RealReal won’t let AI agents hog designer clothingSimilar attack · The Verge (AI)
• HighCVE-2026-115912: vLLM arbitrary Python execution via forged shared-memory multimodal dataSimilar attack · NVD/CVE Database