Federated Complex Qeury Answering
The paper introduces FedCQA, a method to answer complex queries on multi-source knowledge graphs (KGs) while preserving privacy. Current methods focus on single KGs and can’t be applied to multiple…
Continue readingCryptography and Security
The study of securing information and communication systems, including encryption techniques and network security.
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
The research discusses the increasing security threats posed by Large Language Models (LLMs). Traditional jailbreak attacks, designed to assess the security defenses of LLMs, are easily recognized and defended by…
Continue readingEnhancing Multi-Criteria Decision Analysis with AI: Integrating Analytic Hierarchy Process and GPT-4 for Automated Decision Support
The paper presents a new innovative approach to Multiple-criteria Decision Analysis (MCDA) in cybersecurity by integrating the Analytic Hierarchy Process (AHP) and Generative Pre-trained Transformer 4 (GPT-4). The study focuses…
Continue readingSecret Collusion Among Generative AI Agents
This academic paper focuses on the problem of secret collusion among generative AI agents. It formalizes the issue using concepts from AI and security literature, discussing the potential for steganographic…
Continue readingCyberMetric: A Benchmark Dataset for Evaluating Large Language Models Knowledge in Cybersecurity
The paper presents ‘CyberMetric’, a benchmark dataset composed of 10,000 questions from various cybersecurity sources. The dataset’s purpose is to assess and compare the knowledge of large language models (LLMs),…
Continue readingRQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
The article introduces a new approach, RQP-SGD, for privacy-preserving machine learning. The rise of IoT devices necessitates efficient and secure data processing. Traditional machine learning models can be impractical for…
Continue readingPermute-and-Flip: An optimally robust and watermarkable decoder for LLMs
The article centers on a new decoding method named Permute-and-Flip (PF) decoder. This decoder exhibits robustness features akin to the standard sampling decoder, but it is provably up to 2x…
Continue readingPromptCrypt: Prompt Encryption for Secure Communication with Large Language Models
The article introduces PromptCrypt, a novel encryption mechanism designed to enhance user privacy in cloud-based language models (LLMs) like ChatGPT. The method encrypts user inputs with Emoji, making the data…
Continue readingRapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
This paper introduces RIPPLE, an optimization-based method that exploits subconsciousness and echopraxia to jailbreak Large Language Models (LLMs). LLMs, due to their extraordinary reasoning and comprehension abilities, are used widely…
Continue readingHuman-Centered Privacy Research in the Age of Large Language Models
The emergence and increased use of large language models (LLMs) in user-facing systems have led to significant privacy concerns. These concerns have been primarily model-centered, exploring how LLMs lead to…
Continue reading Page 1 of 26 Next