AI · Article
Researchers Hijack Hugging Face Account for Kokoro AI Voice Model via Expired Domain
하이테크정보 ·
At a glance
Security researcher Alon Hertz's team said they took over the Hugging Face publisher account for the open-weight voice model Kokoro by registering a domain listed in the project's DONATE.md file. They then used a password reset through that domain to get the account. Hugging Face did not verify that the original owner still controlled the account.
Key points
- The researchers registered a domain that was listed in the Kokoro repository and used it to reset the account password.
- Hugging Face did not check whether the original owner still controlled the account, and the takeover reportedly happened last weekend.
- Kokoro supports many languages and over 50 voice presets, and is reportedly used in projects linked to Google, Nvidia, AMD, Intel, and AWS.
- In a proof of concept, the team changed the model weights on a common gaming GPU in 87 seconds, making the voice differ from the input text. They tested the altered weights only locally.
Why it matters
Models that are widely downloaded but no longer updated could be targeted this way, and malicious weights might not be caught by standard malware scanners.
Original source
허깅페이스 AI 모델 계정 탈취 실증…"만료 도메인 사서 비밀번호 재설정"
하이테크정보 · Nov 18, 10:04 KST
Read on 하이테크정보 ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to 하이테크정보.
Hugging Face · Ranking and more news
More from this field
- Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
MIT News · Nov 21, 06:00 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST