相关论文: Training Transformers for Information Security Tas…

Self-supervised learning (SSL) is able to build latent representations that generalize well to unseen data. However, only a few SSL techniques exist for the online CL setting, where data arrives in small minibatches, the model must comply…

Recent advancements in language models have demonstrated remarkable improvements in various natural language processing (NLP) tasks such as web navigation. Supervised learning (SL) approaches have achieved impressive performance while…

Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively protect user data, they remain vulnerable to either the server,…

Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which…

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Understanding to what extent neural networks memorize training data is an intriguing question with practical and theoretical implications. In this paper we show that in some cases a significant fraction of the training data can in fact be…

In the face of an increasingly broad cyberattack surface, cyberattack-resilient load forecasting for electric utilities is both more necessary and more challenging than ever. In this paper, we propose an adversarial machine learning (AML)…

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Learned optimizers are increasingly effective, with performance exceeding that of hand designed optimizers such as Adam~\citep{kingma2014adam} on specific tasks \citep{metz2019understanding}. Despite the potential gains available, in…

Malicious software (malware) classification offers a unique challenge for continual learning (CL) regimes due to the volume of new samples received on a daily basis and the evolution of malware to exploit new vulnerabilities. On a typical…

Natural language processing (NLP) tasks tend to suffer from a paucity of suitably annotated training data, hence the recent success of transfer learning across a wide variety of them. The typical recipe involves: (i) training a deep,…

Learning to learn (L2L) trains a meta-learner to assist the learning of a task-specific base learner. Previously, it was shown that a meta-learner could learn the direct rules to update learner parameters; and that the learnt neural…

AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of…

We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization. Our goal is to…

In many interesting cases, the application of machine learning is hindered by data having a complicated structure stimulated by a structured file-formats like JSONs, XMLs, or ProtoBuffers, which is non-trivial to convert to a vector /…

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…

To protect large-scale computing environments necessary to meet increasing computing demand, cloud providers have implemented security measures to monitor Operations and Maintenance (O&M) activities and therefore prevent data loss and…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small number of samples that each possess the backdoor pattern (usually…

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…