ServiceNow AI Research

Cybersecurity

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To …
International Conference on Learning Representations,  2026.
PDF Cite
Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning
Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning
The rise of AI agents that can use tools, browse the web and interact with computers on behalf of a user, has sparked strong interest …
Workshop at the International Conference of Machine Learning (ICML),  2025.
PDF Cite