Adversarial attacks and defenses for large language models (LLMs): methods, frameworks & challenges

Pranjal Kumar

2024International Journal of Multimedia Information Retrieval29 citationsDOI

Topics & Concepts

Adversarial systemOffensiveComputer scienceTransferabilityComputer securityArtificial intelligenceOperations researchMachine learningEngineeringLogitAdversarial Robustness in Machine LearningTopic ModelingHate Speech and Cyberbullying Detection

Adversarial attacks and defenses for large language models (LLMs): methods, frameworks &amp; challenges

Topics & Concepts

Adversarial attacks and defenses for large language models (LLMs): methods, frameworks & challenges