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

Deep learning (DL) models are widely used in real-world applications but remain vulnerable to distribution shifts, especially due to weather and lighting changes. Collecting diverse real-world data for testing the robustness of DL models is…

This paper investigates a novel algorithmic vulnerability when imperceptible image layers confound multiple vision models into arbitrary label assignments and captions. We explore image preprocessing methods to introduce stealth…

The problem of model collapse has presented new challenges in iterative training of generative models, where such training with synthetic data leads to an overall degradation of performance. This paper looks at the problem from a…

Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect.…

Robustness is a fundamental property of machine learning classifiers required to achieve safety and reliability. In the field of adversarial robustness of image classifiers, robustness is commonly defined as the stability of a model to all…

This research examines the emerging technique of step-around prompt engineering in GenAI research, a method that deliberately bypasses AI safety measures to expose underlying biases and vulnerabilities in GenAI models. We discuss how…

The increasing capabilities of artificial intelligence (AI) systems make it ever more important that we interpret their internals to ensure that their intentions are aligned with human values. Yet there is reason to believe that misaligned…

Pre-trained neural language models give high performance on natural language inference (NLI) tasks. But whether they actually understand the meaning of the processed sequences remains unclear. We propose a new diagnostics test suite which…

Often machine learning models tend to automatically learn associations present in the training data without questioning their validity or appropriateness. This undesirable property is the root cause of the manifestation of spurious…

As artificial intelligence (AI) becomes increasingly embedded in the core functions of social, political, and economic life, it catalyzes structural transformations with far-reaching societal implications. This paper advances the concept of…

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

A central question in natural language understanding (NLU) research is whether high performance demonstrates the models' strong reasoning capabilities. We present an extensive series of controlled experiments where pre-trained language…

Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

Subliminal prompting is a phenomenon in which language models are biased towards certain concepts or traits through prompting with semantically unrelated tokens. While prior work has examined subliminal prompting in user-LLM interactions,…

We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding this matter. In this work, we propose an indicator to measure…

As pedestrian navigation increasingly experiments with Generative AI, and in particular Large Language Models, the nature of routing risks transforming from a verifiable geometric task into an opaque, persuasive dialogue. While…

Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%, and in the worst cases, up to 99%. This susceptibility poses great challenges…

Synthetic participants represent a methodologically concerning concept that threatens the integrity of UX research. Findings from previous experiments specify how AI outputs are misaligned with the behaviors and thoughts of real humans in…

Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibility of modern neural networks to small data perturbations.…