Oskar J. Hollinsworth

STACK: Adversarial Attacks on LLM Safeguard Pipelines

2025 · arXiv (Cornell University)

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic and OpenAI guard their latest Opus 4 model and GPT-5 models using such defense pipelines, and other …