Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAIAmbrish RawatStefan Schoepfet al.2024NeurIPS 2024
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven ArgumentationTomas Bueno MomcilovicBeat Buesseret al.2024xAI 2024