English
Related papers

Related papers: The Evaluation Differential: When Frontier AI Mode…

200 papers

In recent years, the popularity of fingerprint-based biometric authentication systems significantly increased. However, together with many advantages, biometric systems are still vulnerable to presentation attacks (PAs). In particular, this…

Computer Vision and Pattern Recognition · Computer Science 2021-01-25 Jascha Kolberg , Marcel Grimmer , Marta Gomez-Barrero , Christoph Busch

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

Computation and Language · Computer Science 2024-01-29 Seonmin Koo , Chanjun Park , Jinsung Kim , Jaehyung Seo , Sugyeong Eo , Hyeonseok Moon , Heuiseok Lim

Most autonomous driving safety benchmarks use time-to-collision (TTC) to assess risk and guide safe behaviour. However, TTC-based methods treat risk as a one-dimensional closing problem, despite the inherently two-dimensional nature of…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…

Machine Learning · Computer Science 2021-09-15 Bin Zhu , Zhaoquan Gu , Le Wang , Zhihong Tian

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

Computers and Society · Computer Science 2023-10-03 Joe O'Brien , Shaun Ee , Zoe Williams

We study causal discovery from a single observed sequence of discrete events generated by a stochastic process, as encountered in vehicle logs, manufacturing systems, or patient trajectories. This regime is particularly challenging due to…

Machine Learning · Computer Science 2026-03-18 Hugo Math , Rainer Lienhart

Autonomous vehicles in interactive traffic environments are often limited by the scarcity of safety-critical tail events in static datasets, which biases learned policies toward average-case behaviors and reduces robustness. Existing…

Robotics · Computer Science 2026-04-10 Yicheng Guo , Jiaqi Liu , Chengkai Xu , Peng Hang , Jian Sun

In economic program evaluation, it is common to obtain panel data in which outcomes are indicators that an individual has reached an absorbing state. For example, they may indicate whether an individual has exited a period of unemployment,…

Econometrics · Economics 2026-05-26 Ben Deaner , Hyejin Ku

Neural network-based approaches have recently shown significant promise in solving partial differential equations (PDEs) in science and engineering, especially in scenarios featuring complex domains or incorporation of empirical data. One…

Machine Learning · Computer Science 2025-03-19 Chuqi Chen , Yahong Yang , Yang Xiang , Wenrui Hao

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

Artificial Intelligence · Computer Science 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

The ever-evolving landscape of attacks, coupled with the growing complexity of ICT systems, makes crafting anomaly-based intrusion detectors (ID) and error detectors (ED) a difficult task: they must accurately detect attacks, and they…

Cryptography and Security · Computer Science 2024-02-15 Tommaso Puccetti , Andrea Ceccarelli

Every AI benchmark operationalizes theoretical assumptions about the capability it claims to assess. When assumptions function as unexamined commitments, benchmarks stabilize the dominant paradigm by narrowing what counts as progress. Over…

Artificial Intelligence · Computer Science 2026-05-15 Theodore J Kalaitzidis

Reliability of deep learning models is critical for deployment in high-stakes applications, where out-of-distribution or adversarial inputs may lead to detrimental outcomes. Evidential Deep Learning, an efficient paradigm for uncertainty…

Machine Learning · Computer Science 2026-03-05 Charmaine Barker , Daniel Bethell , Simos Gerasimou

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs)…

Machine Learning · Computer Science 2021-11-01 Ecenaz Erdemir , Jeffrey Bickford , Luca Melis , Sergul Aydore

Most existing emotion analysis emphasizes which emotion arises (e.g., happy, sad, angry) but neglects the deeper why. We propose Emotion Interpretation (EI), focusing on causal factors-whether explicit (e.g., observable objects,…

Artificial Intelligence · Computer Science 2025-04-18 Yuxiang Lin , Jingdong Sun , Zhi-Qi Cheng , Jue Wang , Haomin Liang , Zebang Cheng , Yifei Dong , Jun-Yan He , Xiaojiang Peng , Xian-Sheng Hua

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Hang-Cheng Dong , Yuhao Jiang , Yibo Jiao , Lu Zou , Kai Zheng , Bingguo Liu , Dong Ye , Guodong Liu

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

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

Artificial Intelligence · Computer Science 2025-11-11 Maheep Chaudhary , Ian Su , Nikhil Hooda , Nishith Shankar , Julia Tan , Kevin Zhu , Ryan Lagasse , Vasu Sharma , Ashwinee Panda

Now that AI-driven moderation has become pervasive in everyday life, we often hear claims that "the AI is biased". While this is often said jokingly, the light-hearted remark reflects a deeper concern. How can we be certain that an online…

Computation and Language · Computer Science 2026-04-02 Subhojit Ghimire

Black-box safety evaluation of AI systems assumes model behavior on test distributions reliably predicts deployment performance. We formalize and challenge this assumption through latent context-conditioned policies -- models whose outputs…

Artificial Intelligence · Computer Science 2026-02-20 Vishal Srivastava
‹ Prev 1 3 4 5 6 7 10 Next ›