相关论文: Subliminal Corruption: Mechanisms, Thresholds, and…

Generative artificial intelligence (AI) is rapidly populating medical records with synthetic content, creating a feedback loop where future models are increasingly at risk of training on uncurated AI-generated data. However, the clinical…

Frontier AI systems require governance mechanisms that can verify internal alignment, not just behavioral compliance. Private governance mechanisms audits, certification, insurance, and procurement are emerging to complement public…

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across…

Language models can transfer hidden biases during distillation. For example, a teacher that "likes owls" can make its student "like owls" too, even when the training data consists only of lists of numbers. This surprising phenomenon is…

Neural network based Artificial Intelligence (AI) has reported increasing scales in experiments. However, this paper raises a rarely reported stage in such experiments called Post-Selection alter the reader to several possible protocol…

In the context of artificial neural networks, subliminal learning refers to the transfer of task-relevant knowledge or unintended biases from teacher to student models through distillation on task-unrelated input$\unicode{x2013}$output…

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

Obtaining human-readable symbolic formulas via genetic programming-based symbolic distillation of a deep neural network trained on the target dataset presents a promising yet underexplored path towards explainable artificial intelligence…

Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real world applications, tend to perform badly. The primary reason is…

To date, various neural methods have been proposed for causal effect estimation based on observational data, where a default assumption is the same distribution and availability of variables at both training and inference (i.e., runtime)…

The growing adoption of artificial intelligence (AI) has amplified concerns about trustworthiness, including integrity, privacy, robustness, and bias. To assess and attribute these threats, we propose ConceptLens, a generic framework that…

As AI systems approach superhuman capabilities, scalable oversight increasingly relies on LLM-as-a-judge frameworks where models evaluate and guide each other's training. A core assumption is that binary preference labels provide only…

Adapting to latent confounded shift remains a core challenge in modern AI. This setting is driven by hidden variables that induce spurious correlations between inputs and outputs during training, leading models to rely on non-causal…

Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-quality images, audios, and videos. They benefit significantly from extensive pre-training on large-scale datasets, including web-crawled data with…

Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance. To alleviate this problem, we present an efficient robust algorithm…

The ability of large language models (LLMs) to $``$learn in context$"$ based on the provided prompt has led to an explosive growth in their use, culminating in the proliferation of AI assistants such as ChatGPT, Claude, and Bard. These AI…

When language models are trained on synthetic data, they (student model) can covertly acquire behavioral traits from the data-generating model (teacher model). Subliminal learning refers to the transmission of traits from a teacher to a…

The inability of DNNs to explain their black-box behavior has led to a recent surge of explainability methods. However, there are growing concerns that these explainability methods are not robust and trustworthy. In this work, we perform…

Recent capability increases in large language models (LLMs) open up applications in which groups of communicating generative AI agents solve joint tasks. This poses privacy and security challenges concerning the unauthorised sharing of…

Time-series models typically assume untainted and legitimate streams of data. However, a self-interested adversary may have incentive to corrupt this data, thereby altering a decision maker's inference. Within the broader field of…