Search Results for author:
Found 20 papers, 1 papers with code
A Generative Caching System for Large Language Models
Caching has the potential to be of significant benefit for accessing large language models (LLMs) due to their high latencies which typically range from a small number of seconds to well over a minute.
Malware Detection at the Edge with Lightweight LLMs: A Performance Evaluation
The rapid evolution of malware attacks calls for the development of innovative detection methods, especially in resource-constrained edge computing.
LMN: A Tool for Generating Machine Enforceable Policies from Natural Language Access Control Rules using LLMs
Organizations often lay down rules or guidelines called Natural Language Access Control Policies (NLACPs) for specifying who gets access to which information and when.
Automated Consistency Analysis of LLMs
In this paper, we have analyzed and developed a formal definition of consistency of responses of LLMs.
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
To understand this vulnerability, we discovered that the deviation from the query's embedding to that of the poisoned document tends to follow a pattern in which the high similarity between the poisoned document and the query is retained, thereby enabling precise retrieval.
Using Retriever Augmented Large Language Models for Attack Graph Generation
As the complexity of modern systems increases, so does the importance of assessing their security posture through effective vulnerability management and threat modeling techniques.
Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
DP-SGD) to significantly boost accuracy and convergence.
Code Hallucination
Generative models such as large language models are extensively used as code copilots and for whole program generation.
LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
To address such limitations, we propose a novel Language Model-based Optimal Differential Privacy (LMO-DP) mechanism, which takes the first step to enable the tight composition of accurately fine-tuning (large) language models with a sub-optimal DP mechanism, even in strong privacy regimes (e. g., $0. 1\leq \epsilon<3$).
Transfer Learning for Security: Challenges and Future Directions
The latter data may follow a distinct distribution.
Trust and ethical considerations in a multi-modal, explainable AI-driven chatbot tutoring system: The case of collaboratively solving Rubik's Cube
Artificial intelligence (AI) has the potential to transform education with its power of uncovering insights from massive data about student learning patterns.
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Subsequently, we employ a classifier that is jointly trained with the watermark to detect the presence of the watermark.
Graphene: Infrastructure Security Posture Analysis with AI-generated Attack Graphs
In this paper, we propose Graphene, an advanced system designed to provide a detailed analysis of the security posture of computing infrastructures.
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety.
Evaluating Chatbots to Promote Users' Trust -- Practices and Open Problems
Chatbots, the common moniker for collaborative assistants, are Artificial Intelligence (AI) software that enables people to naturally interact with them to get tasks done.
When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes
Thus, it is essential to ensure fairness in machine learning models.
Edge Security: Challenges and Issues
Edge computing is a paradigm that shifts data processing services to the network edge, where data are generated.
BeautifAI -- A Personalised Occasion-oriented Makeup Recommendation System
The proposed work's novel contributions, including the incorporation of occasion context, region-wise makeup recommendation, real-time makeup previews and continuous makeup feedback, set our system apart from the current work in makeup recommendation.
Towards Deep Federated Defenses Against Malware in Cloud Ecosystems
In cloud computing environments with many virtual machines, containers, and other systems, an epidemic of malware can be highly threatening to business processes.
Uncheatable Machine Learning Inference
Given a classification service supplier $S$, intermediary CaaS provider $P$ claiming to use $S$ as a classification backend, and customer $C$, our work addresses the following questions: (i) how can $P$'s claim to be using $S$ be verified by $C$?
