Cybersecurity Commons^™

Systematic Approaches To Characterizing Vulnerabilities And Enhancing Robustness Of Text And Vision-Language Models, Poojitha Thota

Computer Science and Engineering Dissertations

The proliferation of artificial intelligence (AI) across critical domains, including news summarization, privacy-policy analysis, and medical decision support, has raised growing concerns about the security and robustness of these systems against adversarial manipulation. This dissertation investigates adversarial robustness in generative AI by addressing three key research goals: (1) characterizing adversarial vulnerabilities across generative models, (2) developing systematic defenses to improve the robustness of generative models, and (3) designing deployment-time safeguards for securing LLM interactions.

Towards the first goal, we characterize adversarial vulnerabilities across text-based and multimodal systems. In abstractive text summarization, we show that inference-time perturbations can exploit lead bias …

Ai-Driven Real-Time Detection Of Zero-Day Browser Exploits Using Webassembly-Based Instrumentation, Temitope Damilola Elijah

College of Graduate Studies: Theses & Dissertations

The rapid evolution of web browsers into fully fledged application execution environments has significantly expanded their attack surface, making them prime targets for sophisticated zero-day exploits that evade traditional signature-based security mechanisms. To address this challenge, this research proposes an AI-driven framework for real-time detection and analysis of zero-day exploits in web browsers by integrating browser-level telemetry monitoring, unsupervised anomaly detection, and large language model–based threat interpretation. The framework introduces a lightweight WebAssembly telemetry agent embedded within the browser runtime to capture low-level execution behaviors, including WASM module instantiation, memory growth patterns, network interactions, and runtime API activity. These telemetry …

When Helpfulness Becomes Harmful: Jailbreaking Llms For Malicious Code Generation, Noelle Capodieci

Electronic Theses & Dissertations (2024 - present)

Generative AI (GenAI) and Large Language Models (LLMs) have made large strides in coding task capabilities, with many software developers integrating agentic engineering into their workflow. While GenAI has largely benefited professional software engineers who can automate their work, it has also created room for those with little coding expertise to also create fully fledged programs and applications. It is commonly noted that GenAI is trained with two major goals in mind: to be as helpful as possible, and be as harmless as possible. There exist moments where helpfulness may be prioritized over harmlessness when these goals conflict. LLMs may …

Context-Switch Attacks: Understanding And Mitigating The Threat To Llm Applications, Sydney Holder, Bivin Sadler

SMU Data Science Review

Large Language Models (LLMs) are transforming conversational AI, yet their dependence on prompt-supplied context exposes them to context-switch attacks that covertly steer dialogue toward sensitive or malicious ends. A 70 one-sided conversation transcript evaluation set was constructed spanning various fraudulent scenarios. Each transcript embeds adversarial patterns drawn while preserving natural conversational flow. We introduce a hybrid defense that pairs a BERT-based semantic-drift detector (cosine-similarity threshold = 0.70) with a curated keyword and hack-phrase scanner to counter these threats. In aggregate, the system delivered 100 % recall, intercepting every simulated phishing or data-harvesting attempt. The keyword layer achieved perfect precision, generating …

Ceker: A Generalizable Llm Framework For Literature Analysis With A Case Study In Unikernel Security, Alex Wollman, John Hastings

Research & Publications

Literature reviews are a critical component of formulating and justifying new research, but are a manual and often time-consuming process. This research introduces a novel, generalizable approach to literature analysis called CEKER which uses a three-step process to streamline the collection of literature, the extraction of key insights, and the summarized analysis of key trends and gaps. Leveraging Large Language Models (LLMs), this methodology represents a significant shift from traditional manual literature reviews, offering a scalable, flexible, and repeatable approach that can be applied across diverse research domains. A case study on unikernel security illustrates CEKER's ability to generate novel …