DeepSeek-R1AIModel 11x More Likely to Generate Harmful Content, Security Research Finds
Markets Insider - Business InsiderCYBERSECURITYRISKS– 78% of cybersecurity tests successfully tricked DeepSeek-R1 into generating insecure or malicious code, including malware, …
Read the original at Markets Insider ↗
- Topics
- Cybersecurity
- Mentions
- DeepSeek
- Tags
- AI Use Case
- Tracked via
- Google Alert “AI Risks”
Same story, other outlets
- DeepSeek-R1AIModel 11x More Likely to Generate Harmful Content, Security Research Finds globenewswire.com · Jan 31, 2025
- DeepSeek-R1AIModel 11x More Likely to Generate Harmful Content, Security Research Finds morningstar.com · Jan 31, 2025