8 papers
ShadowPickle: Evading Machine Learning Model Scanners via Stealthy Pickle Deserialization Attacks
Dhruv Pradhan, Sarang Nambiar, Ezekiel Soremekun
Model hosting hubs (e.g., Hugging Face) are vulnerable to supply chain attacks that enable remote code execution on trusted user environments. Attackers often distribute malicious…
Malicious ML Model Detection by Learning Dynamic Behaviors
Sarang Nambiar, Dhruv Pradhan, Ezekiel Soremekun
Pre-trained machine learning models (PTMs) are commonly provided via Model Hubs (e.g., Hugging Face) in standard formats like Pickles to facilitate accessibility and reuse. However…
MUCOCO: Automated Consistency Testing of Code LLMs
Chua Jin Chou, Khant That Lwin, Ezekiel Soremekun
Code LLMs often portray inconsistent program behaviors. Developers typically employ benchmarks to assess Code LLMs, but most benchmarks are hand-crafted, static and do not target c…
Knowledge-based Consistency Testing of Large Language Models
Sai Sathiesh Rajan, Ezekiel Soremekun, Sudipta Chattopadhyay
In this work, we systematically expose and measure the inconsistency and knowledge gaps of Large Language Models (LLMs). Specifically, we propose an automated testing framework (ca…
Directed Grammar-Based Test Generation
Lukas Kirschner, Ezekiel Soremekun
To effectively test complex software, it is important to generate goal-specific inputs, i.e., inputs that achieve a specific testing goal. However, most state-of-the-art test gener…
HInter: Exposing Hidden Intersectional Bias in Large Language Models
Badr Souani, Ezekiel Soremekun, Mike Papadakis +3
Large Language Models (LLMs) may portray discrimination towards certain individuals, especially those characterized by multiple attributes (aka intersectional bias). Discovering in…