Adversarial Prompting Framework for AI Safety Assessment
For developers and deployers of generative AI models, the framework provides a systematic method to evaluate and quantify vulnerabilities to adversarial prompts, though the approach is incremental.
The paper presents an Adversarial Prompting Framework (APF) for assessing AI safety, demonstrating that encoded prompts achieve the highest success rates in bypassing safety mechanisms in enterprise environments.
Artificial Intelligence (AI), especially Generative AI (GenAI), adoption has increased in industries significantly in recent years. However, the use of these models may also expose systems to new forms of cyberattacks by different malicious actors -- adversarial prompt attack (APA) being one of the most prominent examples of such threats. This paper presents the implementation of an Adversarial Prompting Framework (APF) for a comprehensive assessment of AI safety. The framework systematically evaluates the resilience of the AI model through the generation of structured adversarial prompts at multiple sophistication levels, from direct harmful requests to advanced encoding-based attacks. Our implementation demonstrates the practical application of this methodology in enterprise environments, providing automated testing capabilities with quantitative security assessment metrics. The results indicate significant variations in the model vulnerabilities across different attack vectors, with encoded prompts presenting the highest success rates in bypassing safety mechanisms.