Kaneko, Masahiro

6 publications

ICLR 2026 JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation Under Jailbreak Attacks Masahiro Kaneko, Ayana Niwa, Timothy Baldwin

ICLR 2026 Stopping Computation for Converged Tokens in Masked Diffusion-LM Decoding Daisuke Oba, Danushka Bollegala, Masahiro Kaneko, Naoaki Okazaki

IJCAI 2025 An Ethical Dataset from Real-World Interactions Between Users and Large Language Models Masahiro Kaneko, Danushka Bollegala, Timothy Baldwin

NeurIPS 2025 Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs Masahiro Kaneko, Timothy Baldwin

AAAI 2024 OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples Ryuto Koike, Masahiro Kaneko, Naoaki Okazaki

AAAI 2022 Unmasking the Mask - Evaluating Social Biases in Masked Language Models Masahiro Kaneko, Danushka Bollegala