New TELUS Digital Research Uncovers AI Safety Risks, Offers a Blueprint to Protect Enterprise AI Applications
TELUS Digital released its second annual GenAI Safety Model Benchmark, which evaluated 34 AI models from 10 global providers using over 620,000 adversarial tests. The study found that vulnerability rates ranged from 1.3% to 93%, with reasoning models proving significantly harder to exploit (19.9% vulnerability) than non-reasoning models (55.1%).
Key figures
- Models tested
- 34
- Providers tested
- 10
- Adversarial tests
- 620,000
- Max vulnerability rate
- 93%
- Min vulnerability rate
- 1.3%
- Orgs with ai incidents
- 86%
- Global ai spending 2026
- $2.52 trillion
- Ai security spending 2026
- $3.43 billion
- Reasoning model vulnerability
- 19.9%
- Non reasoning model vulnerability
- 55.1%
AI analysis
The rest of the AI analysis, red flags and sentiment are part of Signal8 Pro.
AI-generated analysis of a public disclosure. Not investment advice; verify against the original document.