One Article Review
| Source |  Techworm |
|---|---|
| Identifiant | 8643848 |
| Date de publication | 2025-01-28 19:37:26 (vue: 2025-01-28 14:56:31) |
| Titre | Security Flaws Found In DeepSeek Leads To Jailbreak |
| Texte | DeepSeek R1, the AI model making all the buzz right now, has been found to have several vulnerabilities that allowed security researchers at the Cyber Threat Intelligence firm Kela to jailbreak it.
Kela tested these jailbreaks around known vulnerabilities and bypassed the restriction mechanism on the chatbot.
This allowed them to jailbreak it across a wide range of scenarios, enabling it to generate malicious outputs, such as ransomware development, fabrication of sensitive content, and detailed instructions for creating toxins and explosive devices.
For instance, the “Evil Jailbreak” method (Prompts the AI model to adopt an “evil” persona), which was able to trick the earlier models of ChatGPT and fixed long back, still works on DeepSeek.
The news comes in while DeepSeek investigates a cyberattack, not allowing new registrations.
“Due to large-scale malicious attacks on DeepSeek’s services, we are temporarily limiting registrations to ensure continued service. Existing users can log in as usual.” DeepSeek’s status page reads.
While it does not confirm what kind of cyberattack disrupts its service, it seems to be a DDoS attack.
DeepSeek is yet to comment on these vulnerabilities.
DeepSeek R1, the AI model making all the buzz right now, has been found to have several vulnerabilities that allowed security researchers at the Cyber Threat Intelligence firm Kela to jailbreak it. Kela tested these jailbreaks around known vulnerabilities and bypassed the restriction mechanism on the chatbot. This allowed them to jailbreak it across a wide range of scenarios, enabling it to generate malicious outputs, such as ransomware development, fabrication of sensitive content, and detailed instructions for creating toxins and explosive devices. For instance, the “Evil Jailbreak” method (Prompts the AI model to adopt an “evil” persona), which was able to trick the earlier models of ChatGPT and fixed long back, still works on DeepSeek. The news comes in while DeepSeek investigates a cyberattack, not allowing new registrations. “Due to large-scale malicious attacks on DeepSeek’s services, we are temporarily limiting registrations to ensure continued service. Existing users can log in as usual.” DeepSeek’s status page reads. While it does not confirm what kind of cyberattack disrupts its service, it seems to be a DDoS attack. DeepSeek is yet to comment on these vulnerabilities. |
| Notes | ★★★ |
| Envoyé | Oui |
| Condensat | “due “evil able across adopt all allowed allowing are around attack attacks back been buzz bypassed can chatbot chatgpt comes comment confirm content continued creating cyber cyberattack ddos deepseek deepseek’s detailed development devices disrupts does earlier enabling ensure existing explosive fabrication firm fixed flaws found generate has have instance instructions intelligence investigates its jailbreak jailbreak” jailbreaks kela kind known large leads limiting log long making malicious mechanism method model models new news not now outputs page persona prompts range ransomware reads registrations researchers restriction right scale scenarios security seems sensitive service services several status such temporarily tested them these threat toxins trick users usual vulnerabilities what which wide works yet “evil” |
| Tags | Ransomware Vulnerability Threat |
| Stories | ChatGPT |
| Move | 
|
L'article ne semble pas avoir été repris aprés sa publication.
L'article ne semble pas avoir été repris sur un précédent.