Research
Research
Research
Research
5,442+ 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…
Decompositional jailbreaks pose a critical threat to large language models (LLMs) by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collecti…
AI integration in automotive perception systems shifts requirements from static specifications to continuously evolving entities shaped by data, models, and operating contexts. When such changes are n…
Lattice reduction smooths the Gram-Schmidt profile, and we use majorization to describe the local swap mechanism behind that smoothing. In this language, each non-degenerate Lov\'asz swap acts as a T-…
Generative AI is being increasingly integrated into web search for the convenience it provides users. In this work, we aim to understand how generative AI disrupts web search by retrieving and present…
The advent of Large Language Models (LLMs) has significantly transformed tasks across Software Engineering. In the context of Business Process Management, LLMs are now being explored as tools to deriv…
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…
Large reasoning models such as DeepSeek-R1 and OpenAI o1 generate extended chains of thought spanning thousands of tokens, yet their integration with retrieval-augmented generation (RAG) remains funda…
Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. D…
Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into web…
Foundation models are routinely fine-tuned for use in particular domains, yet safety assessments are typically conducted only on base models, implicitly assuming that safety properties persist through…
Large language models are increasingly used for code generation, yet the correctness of their outputs depends not only on model capability but also on how tasks are specified. Prior studies demonstrat…
Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between s…
This Article argues that conversations with companion chatbot should be subject to a clear structural distinction between commercial and non-commercial contexts. The insertion of undisclosed promotion…
Semantic Communication (SC) backdoor attacks aim to utilize triggers to manipulate the system into producing predetermined outputs via backdoored shared knowledge. Current SC backdoors adopt monomorph…
Deploying proprietary Deep Neural Networks (DNNs) on commodity edge devices demands hardware-backed Digital Rights Management (DRM) capable of withstanding both software-level and physical adversaries…
Android malware detectors built with machine learning often suffer from temporal bias: models are trained and evaluated without respecting apps' actual release times, inflating accuracy and weakening …
AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trust…
Malware development and detection have undergone significant changes in recent years as modern concepts, such as machine learning, have been used for both adversarial attacks and defense. Despite inte…
This work proposes a structural approach to concept drift detection in malware classification using decision tree rulesets. Classifiers are trained across temporal windows on the EMBER2024 dataset, an…
Free open-access publishing with Google Scholar indexing.
Submission Guide →