Search Results for author:
Found 2 papers, 1 papers with code
MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception
To address this, we propose a methodology combining SHapley Additive exPlanations (SHAP) for feature importance analysis with an innovative Optimal Epsilon technique for conducting evasion attacks.
Attacks on Third-Party APIs of Large Language Models
Large language model (LLM) services have recently begun offering a plugin ecosystem to interact with third-party API services.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
