Related papers: Subliminal Corruption: Mechanisms, Thresholds, and…

The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to objective adjudication. We demonstrate that this assumption is…

As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability (knowing what they do not know, detecting errors, seeking clarification) under adversarial pressure is a critical safety…

As Large Language Models (LLMs) scale in size and complexity, the consequences of failures during training become increasingly severe. A major challenge arises from Silent Data Corruption (SDC): hardware-induced faults that bypass…

Learning correlations from data forms the foundation of today's machine learning (ML) and artificial intelligence research. While contemporary methods enable the automatic discovery of complex patterns, they are prone to failure when…

We present a controlled study of how dataset contamination interacts with the post-training stages now standard in large language model training pipelines. Starting from clean checkpoints of Qwen2.5 (0.5B/1.5B) and Gemma3 (1B/4B), we inject…

We consider a data corruption scenario in the classical $k$ Nearest Neighbors ($k$-NN) algorithm, that is, the testing data are randomly perturbed. Under such a scenario, the impact of corruption level on the asymptotic regret is carefully…

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

Instead of building deep learning models from scratch, developers are more and more relying on adapting pre-trained models to their customized tasks. However, powerful pre-trained models may be misused for unethical or illegal tasks, e.g.,…

Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or…

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…

The alignment between human objectives and machine learning models built on these objectives is a crucial yet challenging problem for achieving Trustworthy AI, particularly when preparing for superintelligence (SI). First, given that SI…

The emergence of synthetic data for privacy protection, training data generation, or simply convenient access to quasi-realistic data in any shape or volume complicates the concept of ground truth. Synthetic data mimic real-world…

Artificial intelligence (AI) is increasingly integrated into modern healthcare, offering powerful support for clinical decision-making. However, in real-world settings, AI systems may experience performance degradation over time, due to…

Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision. Recently, several new data augmentations have been proposed that significantly…

Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…

Large language models (LLMs) often exhibit unexpected errors or unintended behavior, even at scale. While recent work reveals the discrepancy between LLMs and humans in skill compositions, the learning dynamics of skill compositions and the…

Large Language Models such as GPTs (Generative Pre-trained Transformers) exhibit remarkable capabilities across a broad spectrum of applications. Nevertheless, due to their intrinsic complexity, these models present substantial challenges…

Fine-tuning is now the primary method for adapting large neural networks, but it also introduces new integrity risks. An untrusted party can insert backdoors, change safety behavior, or overwrite large parts of a model while claiming only…

We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall performance. Unlike prior poisoning work under static pretraining, we study repeated…

The rapid advancement of AI has expanded its capabilities across domains, yet introduced critical technical vulnerabilities, such as algorithmic bias and adversarial sensitivity, that pose significant societal risks, including…