• Home
  • Blog
    • Business Partner Magazine Archive
  • Resources
  • About Us
    • Cookie Policy
    • Disclosure Policy
    • Privacy Policy
    • Terms of Website Use
  • Contacts

Business Partner Magazine

Tips and advice for entrepreneurs, start-ups and SMEs

  • News
  • Business Success
  • Marketing
  • Employees
  • Technology
  • Start-up
  • Productivity
  • Communication

DeepSeek-R1 AI Model 11x More Likely to Generate Harmful Content, Security Research Finds

January 31, 2025 by BPM Team

Click here to get this post in PDF

Too long to read? Enter your email to download this post as a PDF. We will also send you our best business tips every 2 weeks in our newsletter. You can unsubscribe anytime.

Enter your NameEnter your Email Address
Diverse group of software developers having hacked server and security breach alert

AI Race Between U.S. and China Takes a Dark Turn as Red Teaming Report Uncovers Critical Safety Failures

Boston, Massachusetts – January 31, 2025; The launch of DeepSeek’s R1 AI model has sent shockwaves through global markets, reportedly wiping USD $1 trillion from stock markets.¹ Trump advisor and tech venture capitalist Marc Andreessen described the release as “AI’s Sputnik moment,” underscoring the global national security concerns surrounding the Chinese AI model.²

However, new red teaming research by Enkrypt AI, the world’s leading AI security and compliance platform, has uncovered serious ethical and security flaws in DeepSeek’s technology. The analysis found the model to be highly biased and susceptible to generating insecure code, as well as producing harmful and toxic content, including hate speech, threats, self-harm, and explicit or criminal material. Additionally, the model was found to be vulnerable to manipulation, allowing it to assist in the creation of chemical, biological, and cybersecurity weapons, posing significant global security concerns.

Compared with other models, the research found that DeepSeek’s R1 is:

  • 3x more biased than Claude-3 Opus,
  • 4x more vulnerable to generating insecure code than OpenAI’s O1,
  • 4x more toxic than GPT-4o,
  • 11x more likely to generate harmful output compared to OpenAI’s O1, and;
  • 3.5x 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, said: “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.”

The model exhibited the following risks during testing:

  • BIAS & 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 U.S. Fair Housing Act, posing risks for businesses integrating AI into finance, hiring, and healthcare​.
  • HARMFUL CONTENT & EXTREMISM – 45% of harmful content tests successfully bypassed safety protocols, generating criminal planning guides, illegal weapons information, and extremist propaganda. In one instance, DeepSeek-R1 drafted a persuasive recruitment blog for terrorist organizations, exposing its high potential for misuse​.
  • 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. In contrast, Claude-3 Opus effectively blocked all toxic prompts, highlighting DeepSeek-R1’s weak moderation systems​.
  • CYBERSECURITY RISKS – 78% of cybersecurity tests successfully tricked DeepSeek-R1 into generating insecure or malicious code, including malware, trojans, and exploits. The model was 4.5x more likely than OpenAI’s O1 to generate functional hacking tools, posing a major risk for cybercriminal exploitation.
  • BIOLOGICAL & 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​.

Sahil Agarwal concluded: “As the AI arms race between the U.S. and China intensifies, both nations are pushing the boundaries of next-generation AI for military, economic, and technological supremacy. However, our findings reveal that DeepSeek-R1’s security vulnerabilities could be turned into a dangerous tool—one that cybercriminals, disinformation networks, and even those with biochemical warfare ambitions could exploit. These risks demand immediate attention.”

Also read:

Deepfakes: How they will change corporate and advertising content production

Future AGI Launches World’s Most Accurate Multimodal AI Evaluation Tool

References

1 ‘Sputnik moment’: $1tn wiped off US stocks after Chinese firm unveils AI chatbot – https://www.theguardian.com/business/2025/jan/27/tech-shares-asia-europe-fall-china-ai-deepseek

Nvidia shares sink as Chinese AI app spooks markets – https://www.bbc.co.uk/news/articles/c0qw7z2v1pgo 

2 Marc Andreessen on X – https://x.com/pmarca/status/1883640142591853011 

Image source: elements.envato.com

Filed Under: News, Security, Software, Technology Tagged With: AI, Artificial Intelligence, Cyber security, Data, News, security, software, software development

  • Facebook
  • Instagram
  • LinkedIn
  • Pinterest
  • Twitter
  • YouTube

Disclosure

We earn commissions if you shop through the links on this page.

Recent Posts

  • Top Trends in Milestone Party Themes for 2025
  • Top Causes of Elevator Malfunctions – And How to Prevent Them
  • kyron.bio raises €5.5M to use glycan engineering for advanced drug design
  • Velocity emerges from stealth with $10M to power the velocity of money
  • How to Incorporate Your Company Logo into Custom Workwear Without Compromising Style

Categories

Archives

Tags

Accounting bitcoin brand business growth business skills business success communication cryptocurrency Customer Service Data design Digital marketing ecommerce Efficiency employees Featured Article finance finances Health and Safety infographic insurance Investing investment legal legal services legal tips Management Marketing marketing strategy Outsourcing productivity property Real estate sales security SEO Social Media software starting a business startup Technology Trading Training website workplace

Innovation in Business MarTech Awards – Best SME Business Support Platform 2024 – UK

Innovation in Business MarTech Awards 2024 UK

CorporateLivewire: Innovation & Excellence Awards – Business Publication of the Year

CorporateLivewire: Innovation & Excellence Awards - Business Publication of the Year

Disclosure

We earn commissions if you shop through the links on this page.

Digital Marketing Agency

ReachMore Banner

Business Partner Magazine

Business Partner Magazine provides business tips for small business owners (SME). We are your business partner helping you on your road to business success.

Have a look around the site to discover a wealth of business-focused content.

Here’s to your business success!

Copyright © 2025 - Business Partner Magazine·