English
Related papers

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

200 papers

Neural networks have demonstrated significant accuracy across various domains, yet their vulnerability to subtle input alterations remains a persistent challenge. Conventional methods like data augmentation, while effective to some extent,…

Machine Learning · Computer Science 2023-11-20 Shashank Kotyan , Danilo Vasconcellos Vargas

Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), yet its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content, incorrect responses, and poor OCR quality.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Yunhao Gou , Hansi Yang , Zhili Liu , Kai Chen , Yihan Zeng , Lanqing Hong , Zhenguo Li , Qun Liu , Bo Han , James T. Kwok , Yu Zhang

Deep learning models often face challenges when handling real-world image corruptions. In response, researchers have developed image corruption datasets to evaluate the performance of deep neural networks in handling such corruptions.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-13 Harshitha Machiraju , Michael H. Herzog , Pascal Frossard

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift: agents' tendency to deviate from an original objective. While prior-generation language…

Artificial Intelligence · Computer Science 2026-03-04 Achyutha Menon , Magnus Saebo , Tyler Crosse , Spencer Gibson , Eyon Jang , Diogo Cruz

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Artificial Intelligence · Computer Science 2026-02-17 Igor Santos-Grueiro

In this paper, we introduce a robust transfer regression method designed to handle corrupted labels in target data, under the scenarios that the corruption affects a substantial portion of the labels and the locations of these corruptions…

Methodology · Statistics 2025-02-25 Sheng Pan

The premise of this paper is that compliance with Trustworthy AI governance best practices and regulatory frameworks is an inherently fragmented process spanning across diverse organizational units, external stakeholders, and systems of…

Software Engineering · Computer Science 2021-10-07 Andrew Pery , Majid Rafiei , Michael Simon , Wil M. P. van der Aalst

Artificial Intelligence (AI) is increasingly becoming a trusted advisor in people's lives. A new concern arises if AI persuades people to break ethical rules for profit. Employing a large-scale behavioural experiment (N = 1,572), we test…

Artificial Intelligence · Computer Science 2021-02-16 Margarita Leib , Nils C. Köbis , Rainer Michael Rilke , Marloes Hagens , Bernd Irlenbusch

The goal of machine learning is to develop predictors that generalize well to test data. Ideally, this is achieved by training on an almost infinitely large training data set that captures all variations in the data distribution. In…

Machine Learning · Computer Science 2014-02-28 Laurens van der Maaten , Minmin Chen , Stephen Tyree , Kilian Weinberger

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

In many applications of machine learning (ML), updates are performed with the goal of enhancing model performance. However, current practices for updating models rely solely on isolated, aggregate performance analyses, overlooking important…

Machine Learning · Computer Science 2020-08-12 Megha Srivastava , Besmira Nushi , Ece Kamar , Shital Shah , Eric Horvitz

Complex networked systems can be modeled and represented as graphs, with nodes representing the agents and the links describing the dynamic coupling between them. The fundamental objective of network identification for dynamic systems is to…

Systems and Control · Electrical Eng. & Systems 2020-06-09 Venkat Ram Subramanian , Andrew Lamperski , Murti V. Salapaka

Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual text prompts and…

Cryptography and Security · Computer Science 2024-09-20 Wenxin Ding , Cathy Y. Li , Shawn Shan , Ben Y. Zhao , Haitao Zheng

Large-scale AI models such as GPT-4 have accelerated the deployment of artificial intelligence across critical domains including law, healthcare, and finance, raising urgent questions about trust and transparency. This study investigates…

Artificial Intelligence · Computer Science 2025-10-20 Allen Daniel Sunny

What happens when generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models? Some prior work warns of "model collapse" as the web is overwhelmed by synthetic data; other work…

Machine Learning · Computer Science 2025-03-19 Joshua Kazdan , Rylan Schaeffer , Apratim Dey , Matthias Gerstgrasser , Rafael Rafailov , David L. Donoho , Sanmi Koyejo

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely,…

Computation and Language · Computer Science 2024-07-16 Jérémy Scheurer , Mikita Balesni , Marius Hobbhahn

AI-driven speech-to-text (STT) documentation systems are increasingly adopted in clinical settings to reduce documentation burden and improve workflow efficiency. However, adoption has outpaced systematic evaluation of socio-technical risks…

Human-Computer Interaction · Computer Science 2026-03-31 Nelly Elsayed

As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world,…

Machine Learning · Statistics 2023-10-19 Shide Du , Zihan Fang , Shiyang Lan , Yanchao Tan , Manuel Günther , Shiping Wang , Wenzhong Guo