Related papers: SecPE: Secure Prompt Ensembling for Private and Ro…

Large Language Models (LLMs) are susceptible to security and safety threats, such as prompt injection, prompt extraction, and harmful requests. One major cause of these vulnerabilities is the lack of an instruction hierarchy. Modern LLM…

The wide deployment of the generative pre-trained transformer (GPT) has raised privacy concerns for both clients and servers. While cryptographic primitives can be employed for secure GPT inference to protect the privacy of both parties,…

Federated Prompt Learning has emerged as a communication-efficient and privacy-preserving paradigm for adapting large vision-language models like CLIP across decentralized clients. However, the security implications of this setup remain…

Federated learning (FL) is an emerging paradigm that allows a central server to train machine learning models using remote users' data. Despite its growing popularity, FL faces challenges in preserving the privacy of local datasets, its…

Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence…

Machine Learning (ML) has emerged as one of data science's most transformative and influential domains. However, the widespread adoption of ML introduces privacy-related concerns owing to the increasing number of malicious attacks targeting…

Federated learning (FL) with fully homomorphic encryption (FHE) effectively safeguards data privacy during model aggregation by encrypting local model updates before transmission, mitigating threats from untrusted servers or eavesdroppers…

Collaborative learning enables two or more participants, each with their own training dataset, to collaboratively learn a joint model. It is desirable that the collaboration should not cause the disclosure of either the raw datasets of each…

Large Language Models (LLMs) have been applied to automate cyber security activities and processes including cyber investigation and digital forensics. However, the use of such models for cyber investigation and digital forensics should…

Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in…

We present an approach for generating differentially private synthetic text using large language models (LLMs), via private prediction. In the private prediction framework, we only require the output synthetic data to satisfy differential…

Large language models (LLMs) have achieved remarkable progress across domains and applications but face challenges such as high fine-tuning costs, inference latency, limited edge deployability, and reliability concerns. Small language…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

We introduce \emph{self-jailbreaking}, a threat model in which an aligned LLM guides its own compromise. Unlike most jailbreak techniques, which often rely on handcrafted prompts or separate attacker models, self-jailbreaking requires no…

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check,…

Privacy-preserving machine learning (PPML) is critical to ensure data privacy in AI. Over the past few years, the community has proposed a wide range of provably secure PPML schemes that rely on various cryptography primitives. However,…

Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoption of these primitives is the computational and communication…

The rapid growth of cloud computing and data-driven applications has amplified privacy concerns, driven by the increasing demand to process sensitive data securely. Homomorphic encryption (HE) has become a vital solution for addressing…

Large Language Models (LLMs) have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deployment in inference services such as ChatGPT, concerns about…