A Northwestern University study reveals a security vulnerability in custom GPT programs created by OpenAI, potentially leading to data leaks. The research highlights the risks of prompt extraction and file leakage, with a high success rate in exploiting the vulnerability. Prompt injection attacks have also become a growing concern. The study hopes to prompt the AI community to develop stronger safeguards to balance innovation and security in AI technologies.
Generative AI technology like ChatGPT has sparked concerns about its potential for nefarious purposes. Cyber criminals share tools to recreate malware. AI-enhanced attacks can be combated with threat intelligence sharing and good security practices.
ChatGPT, an AI chatbot, can be tricked into creating code used for malicious software applications. Cybersecurity experts have identified this potential risk and its potential to facilitate criminal activities. As a result, G7 leaders are now addressing the need for appropriate regulations in order to protect society against misuse of this technology. Makoto Miwa, NIST professor and developer of ChatGPT, warned against the security vulnerability and highlighted the need for an international discussion on regulation.
Recently, an independent security analyst & bug hunter Nagli (@naglinagli) discovered a critical security vulnerability in ChatGPT, a widely used and recently released platform. OpenAI, a Microsoft-backed firm, responded quickly by creating a bug bounty program to address the ATO security issue. Unfortunately, reports of hackers selling premium ChatGPT accounts on the dark web were recorded. ChatGPT users are advised to take caution.
. OpenAI, a groundbreaking artificial intelligence (AI) firm, experienced a security incident which led to the temporary ban of its AI chatbot, ChatGPT, in Italy. The Italian Data Protection Authority (Garante) has set changes for OpenAI to comply with, including better security and ability to delete or correct inaccurate personal data. The European Data Protection Board (EDPB) is also looking into AI privacy regulations. OpenAI is working with Garante to make ChatGPT available in Italy soon.