相关论文: Securing Dual-Use Pathogen Data of Concern

Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to routine use, it is important to evaluate their predictive…

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Current metagenomic analysis algorithms require significant computing resources, can report excessive false positives (type I errors), may miss organisms (type II errors / false negatives), or scale poorly on large datasets. This paper…

Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…

Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics. Since deep learning is known to be…

Control evaluations measure whether monitoring and security protocols for AI systems prevent intentionally subversive AI models from causing harm. Our work presents the first control evaluation performed in an agent environment. We…

Sharing health and behavioral data raises significant privacy concerns, as conventional de-identification methods are susceptible to privacy attacks. Differential Privacy (DP) provides formal guarantees against re-identification risks, but…

The growing reliance of intelligent systems on data makes the systems vulnerable to data poisoning attacks. Such attacks could compromise machine learning or deep learning models by disrupting the input data. Previous studies on data…

The wide use of machine learning is fundamentally changing the software development paradigm (a.k.a. Software 2.0) where data becomes a first-class citizen, on par with code. As machine learning is used in sensitive applications, it becomes…

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

Double machine learning (DML) has become an increasingly popular tool for automated variable selection in high-dimensional settings. Even though the ability to deal with a large number of potential covariates can render…

The expanding role of Artificial Intelligence (AI) in diverse engineering domains highlights the challenges associated with deploying AI models in new operational environments, involving substantial investments in data collection and model…

Leveraging real-world health data for machine learning tasks requires addressing many practical challenges, such as distributed data silos, privacy concerns with creating a centralized database from person-specific sensitive data, resource…

Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language…

When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior.…

Clinical trials are pivotal for developing new medical treatments but typically carry risks such as patient mortality and enrollment failure that waste immense efforts spanning over a decade. Applying artificial intelligence (AI) to predict…

As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that…

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Machine learning has revolutionized numerous domains, playing a crucial role in driving advancements and enabling data-centric processes. The significance of data in training models and shaping their performance cannot be overstated. Recent…

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…