The launch of China’sDeepSeek’s R1 AI model sent shockwaves through global markets, reportedly wiping $1 trillion from stock markets in just a couple of days.
Marc Andreeses, an advisor to US president Donald Trump advisor and a tech venture capitalist descibes the release as “AI’s Sputnik moment”.
But now, new red teaming research by Enkrypt AI says it has uncovered what could be serious ethical and security flaws in DeepSeek’s technology.
Compared with other models, the research concludes that DeepSeek’s R1 is:
- 3-times more biased than Claude-3 Opus;
- 4-times more vulnerable to generating insecure code than OpenAI’s O1;
- 4-times more toxic than GPT-4o;
- 11-times more likely to generate harmful output compared to OpenAI’s O1; and
- 3,5-times more likely to produce Chemical, Biological, Radiological, and Nuclear (CBRN) content than OpenAI’s O1 and Claude-3 Opus.
Sahil Agarwal, CEO of Enkrypt AI, comments: “DeepSeek-R1 offers significant cost advantages in AI deployment, but these come with serious risks. Our research findings reveal major security and safety gaps that cannot be ignored.
“While DeepSeek-R1 may be viable for narrowly scoped applications, robust safeguards – including guardrails and continuous monitoring – are essential to prevent harmful misuse.
“AI safety must evolve alongside innovation, not as an afterthought.”
Enkrypt AI reports that the model exhibited the following risks during testing:
- Bias and discrimination – 83% of bias tests successfully produced discriminatory output, with severe biases in race, gender, health, and religion. These failures could violate global regulations such as the EU AI Act and US Fair Housing Act.
- Harmful content and extremism – 45% of harmful content tests successfully bypassed safety protocols, generating criminal planning guides, illegal weapons information, and extremist propaganda.
- Toxic language – The model ranked in the bottom 20th percentile for AI safety, with 6,68% of responses containing profanity, hate speech, or extremist narratives.
- Cybersecurity risks – 78% of cybersecurity tests successfully tricked DeepSeek-R1 into generating insecure or malicious code, including malware, trojans, and exploits.
- Biological and chemical threats – DeepSeek-R1 was found to explain in detail the biochemical interactions of sulfur mustard (mustard gas) with DNA, a clear biosecurity threat. The report warns that such CBRN-related AI outputs could aid in the development of chemical or biological weapons.