Publications (46)
DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation
Hyeseon An, Shinwoo Park, Suyeon Woo +1
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawe…
Obfuscation Rules for Detecting and Detoxifying Korean Toxicity
Yejin Lee, Su-Hyeon Kim, Hyundong Jin +3
As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on n…
LST: Lexicon-Guided Self-Training for Few-Shot Text Classification
Hazel Kim, Jaeman Son, Yo-Sub Han
Self-training provides an effective means of using an extremely small amount of labeled data to create pseudo-labels for unlabeled data. Many state-of-the-art self-training approac…
Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
Jungin Kim, Shinwoo Park, Yo-Sub Han
Identifying LLM-generated code through watermarking poses a challenge in preserving functional correctness. Previous methods rely on the assumption that watermarking high-entropy t…
ECO: Enhanced Code Optimization via Performance-Aware Prompting for Code-LLMs
Su-Hyeon Kim, Joonghyuk Hahn, Sooyoung Cha +1
Code runtime optimization-the task of rewriting a given code to a faster one-remains challenging, as it requires reasoning about performance trade-offs involving algorithmic and st…
A Speculative Parallel DFA Membership Test for Multicore, SIMD and Cloud Computing Environments
Yousun Ko, Minyoung Jung, Yo-Sub Han +1
We present techniques to parallelize membership tests for Deterministic Finite Automata (DFAs). Our method searches arbitrary regular expressions by matching multiple bytes in para…
ContractEval: A Benchmark for Evaluating Contract-Satisfying Assertions in Code Generation
Soohan Lim, Joonghyuk Hahn, Hyunwoo Park +2
Current code generation evaluation measures functional correctness on well-formed inputs that satisfy all input preconditions. This paradigm has a critical limitation: task descrip…
A general architecture of oritatami systems for simulating arbitrary finite automata
Yo-Sub Han, Hwee Kim, Yusei Masuda +1
In this paper, we propose an architecture of oritatami systems with which one can simulate an arbitrary nondeterministic finite automaton (NFA) in a unified manner. The oritatami s…
How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs
Su-Hyeon Kim, Hyundong Jin, Yejin Lee +1
Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors.…
CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
Su-Hyeon Kim, Hyundong Jin, Yejin Lee +1
While modern LLMs are aligned to refuse harmful requests, it is essential to understand the underlying mechanistic basis of this refusal behavior for model safety analysis. For exa…
Detection of LLM-Paraphrased Code and Identification of the Responsible LLM Using Coding Style Features
Shinwoo Park, Hyundong Jin, Jeong-won Cha +1
Recent progress in large language models (LLMs) for code generation has raised serious concerns about intellectual property protection. Malicious users can exploit LLMs to produce…
ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification
Hazel Kim, Daecheol Woo, Seong Joon Oh +2
Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great p…
MECO: Multi-Expert Consensus for Code Time Complexity Prediction
Joonghyuk Hahn, Soohan Lim, Yo-Sub Han
Predicting the complexity of source code is essential for software development and algorithm analysis. Recently, Baik et al. (2025) introduced CodeComplex for code time complexity…
RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
Hyundong Jin, Joonghyuk Hahn, Yo-Sub Han
Large language models (LLMs) show strong performance across natural language processing (NLP), mathematical reasoning, and programming, and recent large reasoning models (LRMs) fur…
Nondeterministic State Complexity for Suffix-Free Regular Languages
Yo-Sub Han, Kai Salomaa
We investigate the nondeterministic state complexity of basic operations for suffix-free regular languages. The nondeterministic state complexity of an operation is the number of s…
Impact of Large Language Models of Code on Fault Localization
Suhwan Ji, Sanghwa Lee, Changsup Lee +2
Identifying the point of error is imperative in software debugging. Traditional fault localization (FL) techniques rely on executing the program and using the code coverage matrix…
DLM-SWAI: Steering Diffusion Language Models Before They Unmask
Hyeseon An, Yo-Sub Han
Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enabl…
Steering Language Models Before They Speak: Logit-Level Interventions
Hyeseon An, Shinwoo Park, Hyundong Jin +1
Controllable generation requires language models to realize output characteristics such as reading level, politeness, and toxicity. Existing steering methods are often indirect, re…
Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
Su-Hyeon Kim, Yo-Sub Han
Large language models from different families use different hidden dimensions, tokenizers, and training procedures, making behavioral directions difficult to compare or transfer ac…
ReSyn: A Generalized Recursive Regular Expression Synthesis Framework
Seongmin Kim, Hyunjoon Cheon, Su-Hyeon Kim +2
Existing Programming-By-Example (PBE) systems often rely on simplified benchmarks that fail to capture the high structural complexity of real-world regexes, such as deeper nesting…
TRAPDOC: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents
Hyundong Jin, Sicheol Sung, Shinwoo Park +2
The reasoning, writing, text-editing, and retrieval capabilities of proprietary large language models (LLMs) have advanced rapidly, providing users with an ever-expanding set of fu…
ATHENA: Mathematical Reasoning with Thought Expansion
JB. Kim, Hazel Kim, Joonghyuk Hahn +1
Solving math word problems depends on how to articulate the problems, the lens through which models view human linguistic expressions. Real-world settings count on such a method ev…
Adaptive Steering and Remasking for Safe Generation in Diffusion Language Models
Yejin Lee, Yo-Sub Han
Diffusion Language Models (DLMs) provide a promising alternative to autoregressive language models by generating text through iterative denoising and bidirectional refinement. Howe…
Linguistics-Aware Non-Distortionary LLM Watermarking
Shinwoo Park, Hyejin Park, Hyeseon An +1
Watermarking should identify language-model output without degrading quality or limiting verification to the model provider. Multilingual deployment makes this harder because morph…
EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models
Hyundong Jin, Yo-Sub Han
Controlling language model outputs is essential for ensuring structural validity, reliability, and downstream usability, and diffusion language models are no exception. Recent adva…
LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming
Sicheol Sung, Aditi, Dogyu kim +2
Automated Test Case Generation (ATCG) is crucial for evaluating software reliability, particularly in competitive programming where robust algorithm assessments depend on diverse a…
CodeComplex: Dataset for Worst-Case Time Complexity Prediction
Seung-Yeop Baik, Joonghyuk Hahn, Jungin Kim +4
Reasoning ability of Large Language Models (LLMs) is a crucial ability, especially in complex decision-making tasks. One significant task to show LLMs' reasoning capability is code…
Site-Directed Insertion: Decision Problems, Maximality and Minimality
Da-Jung Cho, Yo-Sub Han, Kai Salomaa +1
Site-directed insertion is an overlapping insertion operation that can be viewed as analogous to the overlap assembly or chop operations that concatenate strings by overlapping a s…
Outfix-guided insertion
Da-Jung Cho, Yo-Sub Han, Timothy Ng +1
Motivated by work on bio-operations on DNA strings, we consider an outfix-guided insertion operation that can be viewed as a generalization of the overlap assembly operation on str…
Repairing Regex Vulnerabilities via Localization-Guided Instructions
Sicheol Sung, Joonghyuk Hahn, Yo-Sub Han
Regular expressions (regexes) are foundational to modern computing for critical tasks like input validation and data parsing, yet their ubiquity exposes systems to regular expressi…
SAGE:Specification-Aware Grammar Extraction for Automated Test Case Generation with LLMs
Aditi, Hyunwoo Park, Sicheol Sung +2
Grammar-based test case generation has proven effective for competitive programming problems, but generating valid and general grammars from natural language specifications remains…
WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking
Shinwoo Park, Hyejin Park, Hyeseon Ahn +1
Large language models now draft news, legal analyses, and software code with human-level fluency. At the same time, regulations such as the EU AI Act mandate that each synthetic pa…
Cyclic Oritatami Systems Cannot Fold Infinite Fractal Curves
Yo-Sub Han, Hwee Kim
RNA cotranscriptional folding is the phenomenon in which an RNA transcript folds upon itself while being synthesized out of a gene. The oritatami system (OS) is a computation model…
TCProF: Time-Complexity Prediction SSL Framework
Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim +2
Time complexity is a theoretic measure to determine the amount of time the algorithm needs for its execution. In reality, developers write algorithms into code snippets within limi…
RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection
Yejin Lee, Hyeseon Ahn, Yo-Sub Han
Hate speech remains prevalent in human society and continues to evolve in its forms and expressions. Modern advancements in internet and online anonymity accelerate its rapid sprea…
A Framework for Quantum Finite-State Languages with Density Mapping
SeungYeop Baik, Sicheol Sung, Yo-Sub Han
A quantum finite-state automaton (QFA) is a theoretical model designed to simulate the evolution of a quantum system with finite memory in response to sequential input strings. We…
STAB: Specification-driven Testing for Algorithmic Bottlenecks
Soohan Lim, Joonghyuk Hahn, Hyundong Jin +1
Evaluating the efficiency of algorithmic code requires test cases that expose runtime bottlenecks. Previous methods generate efficiency test cases either by increasing input size o…
Neuro-Symbolic Regex Synthesis Framework via Neural Example Splitting
Su-Hyeon Kim, Hyunjoon Cheon, Yo-Sub Han +1
Due to the practical importance of regular expressions (regexes, for short), there has been a lot of research to automatically generate regexes from positive and negative string ex…
Sequential Behavioral Watermarking for LLM Agents
Hyeseon An, Shinwoo Park, Dongsu Kim +1
LLM-based agents act through sequences of executable decisions, but their trajectories provide little evidence of which agent or policy produced them, making provenance, ownership,…
URECA: The Chain of Two Minimum Set Cover Problems exists behind Adaptation to Shifts in Semantic Code Search
Seok-Ung Choi, Joonghyuk Hahn, Yo-Sub Han
Adaptation is to make model learn the patterns shifted from the training distribution. In general, this adaptation is formulated as the minimum entropy problem. However, the minimu…
AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection
Yejin Lee, Joonghyuk Hahn, Hyeseon Ahn +1
Implicit hate speech detection is challenging due to its subtlety and reliance on contextual interpretation rather than explicit offensive words. Current approaches rely on contras…
OPERA: Reasoning about continuous common knowledge in asynchronous distributed systems
Sang-Min Choi, Jiho Park, Quan Nguyen +5
This paper introduces a new family of consensus protocols, namely \emph{Lachesis-class} denoted by , for distributed networks with guaranteed Byzantine fault tolerance…
KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature Analysis
Shinwoo Park, Shubin Kim, Do-Kyung Kim +1
The rapid advancement of large language models (LLMs) increases the difficulty of distinguishing between human-written and LLM-generated text. Detecting LLM-generated text is cruci…
When LLM Essays Outscore Student Essays: What a Korean Writing Rubric Rewards and Where Readers Disagree
Shinwoo Park, Yo-Sub Han
LLMs now help students plan, draft, and revise essays. Educational assessment therefore faces a basic question: how should student and LLM writing be compared? Rubrics assign point…
NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
Hyundong Jin, Yo-Sub Han
Controlling Large Language Models (LLMs) to prevent the generation of undesirable content, such as profanity and personally identifiable information (PII), has become increasingly…
A Linguistics-Aware LLM Watermarking via Syntactic Predictability
Shinwoo Park, Hyejin Park, Hyeseon An +1
As large language models (LLMs) continue to advance rapidly, reliable governance tools have become critical. Publicly verifiable watermarking is particularly essential for fosterin…