CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
Jois, Matthew Green, and Aviel D
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Conceptual steganography encodes covert information in high-level reasoning patterns within LM chains-of-thought, remaining robust to paraphrase defenses while preserving reasoning utility.
citing papers explorer
-
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
-
Conceptual Steganography
Conceptual steganography encodes covert information in high-level reasoning patterns within LM chains-of-thought, remaining robust to paraphrase defenses while preserving reasoning utility.