Işıl Özgü

Işıl Özgü

Ph.D. student at UCLA SEAL Lab

Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

Accurate and Low-Cost Residual Risk Assessment via Sampled Profiling and Structure-Aware Coverage Amplification

Published in Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE '26), 2026

A risk assessment method for black-box fuzzing that replaces coverage instrumentation with hardware-enabled instruction pointer sampling and must-execute analysis, achieving 4.27x higher throughput while maintaining high accuracy.

Recommended citation: Seongmin Lee, Işıl Özgü, Marcel Böhme, and Miryung Kim. 2026. "Accurate and Low-Cost Residual Risk Assessment via Sampled Profiling and Structure-Aware Coverage Amplification." In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE '26), October 12–16, 2026, Munich, Germany. ACM, New York, NY, USA, 12 pages. https://doi.org/10.1145/3832783.3837519
Download Paper

Preprints

The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding

Published in arXiv preprint arXiv:2608.10137 [cs.CL], 2026

A method for correcting the distributional bias that token masking introduces in grammar-constrained decoding, by applying logit correction conditioned on the syntactic/lexical parser state and candidate next tokens, reusing state already computed during incremental parsing.

Recommended citation: Işıl Özgü, Yaoxuan Wu, Guy Van den Broeck, and Miryung Kim. 2026. "The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding." arXiv preprint arXiv:2608.10137.
Download Paper