Research
Research
Research
Research
2,953+ open-access research outputs.
Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack pa…
Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be view…
We introduce a new logic, called \emph{cluster first-order logic}, a restricted fragment of first-order logic specifically designed to study order invariance. An order-invariant formula is one on a vo…
As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables si…
Dynamic spectrum sharing (DSS) played an important role in the 4G-to-5G transition by allowing 5G new radio (NR) to enter valuable legacy spectrum without immediate static refarming. Yet practical dep…
Rewriting Induction (RI) is a formal system in term rewriting to establish program equivalence. The recently defined Bounded RI for higher-order Logically Constrained Term Rewriting Systems (LCSTRSs) …
Software quality assurance remains a major challenge in industrial environments, where large-scale and long-lived systems inevitably accumulate defects. Identifying the location of a fault is often ti…
Generative linguistic steganography (GLS) enables covert communication by embedding secret messages into the natural language generation process. In practical deployment, however, GLS is vulnerable to…
This is the authors response to commentaries on the original article H is for Human and How (Not) to Evaluate Qualitative Research in HCI, https://doi.org/10.1080/07370024.2025.2475743 Commentaries we…
Current cyber attribution approaches typically operate on a per-incident basis, leaving open whether aggregating evidence across campaigns improves adversary identification. We investigate whether cro…
Make America Healthy Again (MAHA) is a health-related campaign slogan proposed by Robert F. Kennedy Jr. and later incorporated into the political coalition of President Trump. While #MAHA quickly circ…
Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memory, invoke external tools, and coordinate with peer…
Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manually tuned hyperparameters rather than fully learnable filters. We show that this challenge st…
This paper presents a semantic-enhanced receiver framework for transmitting natural language sentences over noisy wireless channels using multiple short block codes. After ASCII encoding, the sentence…
Non-Markovian (renewal) epidemic simulation on multi-million-node contact networks is essential for realistic forecasting under general age-dependent holding-time distributions (log-normal, Weibull, E…
Steganography embeds secret messages in seemingly innocuous carriers for covert communication under surveillance. Current Provably Secure Steganography (PSS) schemes based on language models can guara…
Modern retrieval-augmented generation (RAG) systems treat vector embeddings as static, context-free artifacts: an embedding has no notion of when it was created, how trustworthy its source is, or whic…
The informativeness of security-related commit messages is crucial for patch triage: when high, it enables the rapid distribution and deployment of security fixes. Prior research (Reis et al., 2023) r…
Reliable biomedical and clinical retrieval requires more than strong ranking performance: it requires a practical way to find systematic model failures and curate the training evidence needed to corre…
Cyber Threat Intelligence (CTI) reports contain Indicators of Compromise (IOCs) that are critical for security operations. To operationalize these IOCs across heterogeneous logs, analysts often conver…
Free open-access publishing with Google Scholar indexing.
Submission Guide →