Using ChatGPT to cheat on assignments? New tool detects AI-generated text with amazing accuracy
Scientists have developed a ChatGPT detector with unprecedented accuracy. Even though it has a limited scope, this could be a big step forward.
Read moreScientists have developed a ChatGPT detector with unprecedented accuracy. Even though it has a limited scope, this could be a big step forward.
Read moreIT-SA Expo & Congress claims to be Europe’s largest trade fair for IT security. And it really covers a wide range of…
Read moreCategories: News Categories: Ransomware Tags: IT-SA Tags: ransomware Tags: AI Tags: ChatGPT Tags: NIS2 The major talking points IT-SA included ransomware, ChatGPT, and NIS2. |
The post The hot topics from Europe’s largest trade fair for IT security appeared first on Malwarebytes Labs.
Read moreCategories: News Tags: AI Tags: ML Tags: LLM Tags: chatgpt Tags: data poisoning Tags: SQL Tags: prompt injection The NCSC has warned about integrating LLMs into your own services or platforms. Prompt injection and data poisoning are just some of the risks. |
The post Prompt injection could be the SQL injection of the future, warns NCSC appeared first on Malwarebytes Labs.
Read moreCredit to Author: BrianKrebs| Date: Tue, 08 Aug 2023 17:37:23 +0000
WormGPT, a private new chatbot service advertised as a way to use Artificial Intelligence (AI) to help write malicious software without all the pesky prohibitions on such activity enforced by ChatGPT and Google Bard, has started adding restrictions on how the service can be used. Faced with customers trying to use WormGPT to create ransomware and phishing scams, the 23-year-old Portuguese programmer who created the project now says his service is slowly morphing into “a more controlled environment.” The large language models (LLMs) made by ChatGPT parent OpenAI or Google or Microsoft all have various safety measures designed to prevent people from abusing them for nefarious purposes — such as creating malware or hate speech. In contrast, WormGPT has promoted itself as a new LLM that was created specifically for cybercrime activities.
Read moreCredit to Author: Jagadeesh Chandraiah| Date: Wed, 02 Aug 2023 10:00:40 +0000
CryptoRom” fake crypto-trading mobile apps pushed through AI-assisted romance scam, using ChatGPT to lure targets.
Read moreCategories: News Tags: Cisco Tags: Zyxel Tags: ChatGPT Tags: Malvertising Tags: Apple Tags: Google Tags: insider threat Tags: Pentagon explosion Tags: CISA Tags: ransomware guide Tags: Rheinmetall Tags: BlackBasta Tags: WordPress A list of topics we covered in the week of May 22- 28 of 2023 |
The post A week in security (May 22-28) appeared first on Malwarebytes Labs.
Read moreCredit to Author: Vladislav Tushkanov| Date: Wed, 17 May 2023 18:24:19 +0000
Some examples of jailbreaks to get ChatGPT to bypass its creators’ restrictions.
Read more