Related papers: Watermarking Pre-trained Language Models with Back…

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our…

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…

Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However,…

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these…

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…

The rapid advancement of pre-trained language models (PLMs) has demonstrated promising results for various code-related tasks. However, their effectiveness in detecting real-world vulnerabilities remains a critical challenge. While existing…

LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of…

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Large language models (LLMs) have achieved remarkable success across natural language processing tasks, yet their widespread deployment raises pressing concerns around privacy, copyright, security, and bias. Machine unlearning has emerged…

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…

The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights…

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models (LMs). However, the robustness of the watermarking schemes has not been…

Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also growing concerns regarding the potential security issues in the…

Fine-tuned pre-trained language models (PLMs) have achieved awesome performance on almost all NLP tasks. By using additional prompts to fine-tune PLMs, we can further stimulate the rich knowledge distributed in PLMs to better serve…

Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance than their counterparts directly trained on the downstream tasks. In this work, we study what…

The evolution of Large Language Models (LLMs) into agentic systems that perform autonomous reasoning and tool use has created significant intellectual property (IP) value. We demonstrate that these systems are highly vulnerable to imitation…

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is…