Related papers: Beyond Pattern Matching: Seven Cross-Domain Techni…
Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…
Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning…
In this paper, we focus on the problem of dynamically analysing concurrent software against high-level temporal specifications. Existing techniques for runtime monitoring against such specifications are primarily designed for sequential…
Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed…
Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts…
Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA methods typically…
Recent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the success of techniques depends on various parameters, such as…
Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical tasks remains insufficiently examined, particularly under structured human evaluation.…
Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains. Developers and end-users interact with these systems through the use of prompting and prompt engineering.…
Architectural tactics (ATs), as the concrete implementation of architectural decisions in code, address non-functional requirements of software systems. Due to the implicit nature of architectural knowledge in code implementation,…
In the past few years, Language Models (LMs) have shown par-human capabilities in several domains. Despite their practical applications and exceeding user consumption, they are susceptible to jailbreaks when malicious input exploits the…
Application Programming Interface (API) Injection attacks refer to the unauthorized or malicious use of APIs, which are often exploited to gain access to sensitive data or manipulate online systems for illicit purposes. Identifying actors…
Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…
Contrastively trained text-image models have the remarkable ability to perform zero-shot classification, that is, classifying previously unseen images into categories that the model has never been explicitly trained to identify. However,…
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…
As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…
Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…
The integration of additional modalities increases the susceptibility of large vision-language models (LVLMs) to safety risks, such as jailbreak attacks, compared to their language-only counterparts. While existing research primarily…
Modern software systems are increasingly developed within rapid continuous integration and deployment (CI/CD) pipelines, where ensuring security prior to release presents significant technical and organizational challenges. Traditional…
This Monte Carlo simulation examines how prompt engineering strategies shape the quality of large language model (LLM)--generated personality assessment items within the AI-GENIE framework for generative psychometrics. Item pools targeting…