Related papers: Anti-adversarial Learning: Desensitizing Prompts f…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Large language models (LLMs) have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by…

Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not update the pre-trained model's parameters. Instead, it only…

The rise of large language models (LLMs) has introduced new privacy challenges, particularly during inference where sensitive information in prompts may be exposed to proprietary LLM APIs. In this paper, we address the problem of formally…

In recent years, large language models (LLMs) have significantly advanced the field of natural language processing (NLP). By fine-tuning LLMs with data from specific scenarios, these foundation models can better adapt to various downstream…

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed…

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such…

Large Language Models (LLMs) are vulnerable to jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires a time-consuming search for adversarial prompts, whereas automatic adversarial…

An increasing number of companies have begun providing services that leverage cloud-based large language models (LLMs), such as ChatGPT. However, this development raises substantial privacy concerns, as users' prompts are transmitted to and…

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Federated learning (FL) has enabled global model training on decentralized data in a privacy-preserving way by aggregating model updates. However, for many natural language processing (NLP) tasks that utilize pre-trained language models…

Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated…

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Large language models (LLMs) have shown promising potential for next Point-of-Interest (POI) recommendation. However, existing methods only perform direct zero-shot prompting, leading to ineffective extraction of user preferences,…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…