Security News > 2025 > April > New Reports Uncover Jailbreaks, Unsafe Code, and Data Theft Risks in Leading AI Systems
2025-04-29 16:18
Various generative artificial intelligence (GenAI) services have been found vulnerable to two types of jailbreak attacks that make it possible to produce illicit or dangerous content. The first of the two techniques, codenamed Inception, instructs an AI tool to imagine a fictitious scenario, which can then be adapted into a second scenario within the first one where there exists no safety
News URL
https://thehackernews.com/2025/04/new-reports-uncover-jailbreaks-unsafe.html
Related news
- Consumer Reports calls out slapdash AI voice-cloning safeguards (source)
- Red Report 2025: Unmasking a 3X Spike in Credential Theft and Debunking the AI Hype (source)
- CERT-UA Reports Cyberattacks Targeting Ukrainian State Systems with WRECKSTEEL Malware (source)
- Meta Launches LlamaFirewall Framework to Stop AI Jailbreaks, Injections, and Insecure Code (source)