Table 3 presents comprehensive details of the TrojAI dataset. PICCOLO is a backdoor scanning tool aiming at detecting whether a language model is backdoored. It cannot reverse engineer exact triggers but optimizes a list of surrogate triggers that can induce ASR. The surrogate triggers by PICCOLO cannot be directly used. Table 4 documents the optimal prompts identified via fuzzing for each model.

The Rashomon set is the set of models that are approximately as good as the best model in the class. That is, it is the set of all good models.

Hardware-specific optimizations in machine learning (ML) frameworks can cause numerical deviations of inference results. Quite surprisingly, despite using a fixed trained model and fixed input data, inference results are not consistent across platforms, and sometimes not even deterministic on the same platform. We study the causes of these numerical deviations for convolutional neural networks (CNN) on realistic end-to-end inference pipelines and in isolated experiments. Results from 75 distinct platforms suggest that the main causes of deviations on CPUs are differences in SIMD use, and the selection of convolution algorithms at runtime on GPUs. We link the causes and propagation effects to properties of the ML model and evaluate potential mitigations. We make our research code publicly available.

Both of the techniques assume bitwise access to the oracle as a classical function.

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models.