English
Related papers

Related papers: Capability-Oriented Training Induced Alignment Ris…

200 papers

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Machine Learning · Computer Science 2026-05-28 Mohammad Taufeeque , Stefan Heimersheim , Adam Gleave , Chris Cundy

The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both research and industry. Considering the resource-intensive nature…

Machine Learning · Computer Science 2023-08-21 Dominik Hintersdorf , Lukas Struppek , Kristian Kersting

In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…

Machine Learning · Computer Science 2021-01-29 Sobhan Miryoosefi , Kianté Brantley , Hal Daumé , Miroslav Dudik , Robert Schapire

Reinforcement learning has become a powerful paradigm for improving the capability of intelligent systems, but its practical deployment faces two central challenges. First, reinforcement learning must scale efficiently in distributed…

Machine Learning · Computer Science 2026-05-12 Guangchen Lan

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

Machine Learning · Statistics 2025-03-28 Pin-Yu Chen , Han Shen , Payel Das , Tianyi Chen

Software, while beneficial, poses potential cybersecurity risks due to inherent vulnerabilities. Detecting these vulnerabilities is crucial, and deep learning has shown promise as an effective tool for this task due to its ability to…

Software Engineering · Computer Science 2024-01-17 Imam Nur Bani Yusuf , Lingxiao Jiang

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

Machine Learning · Computer Science 2022-12-27 Justin Leo , Jugal Kalita

Deep Reinforcement Learning (RL) has shown promise in addressing complex robotic challenges. In real-world applications, RL is often accompanied by failsafe controllers as a last resort to avoid catastrophic events. While necessary for…

Robotics · Computer Science 2023-09-26 Jakob Thumm , Guillaume Pelat , Matthias Althoff

Large language model (LLM) systems increasingly power everyday AI applications such as chatbots, computer-use assistants, and autonomous robots, where performance often depends on manually well-crafted prompts. LLM-based prompt optimizers…

Machine Learning · Computer Science 2026-01-14 Andrew Zhao , Reshmi Ghosh , Vitor Carvalho , Emily Lawton , Keegan Hines , Gao Huang , Jack W. Stokes

Numerous algorithms have been proposed to $\textit{align}$ language models to remove undesirable behaviors. However, the challenges associated with a very large state space and creating a proper reward function often result in various…

Computation and Language · Computer Science 2024-06-06 Suraj Anand , David Getzen

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…

While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain…

Computation and Language · Computer Science 2024-01-05 Andrew Lee , Xiaoyan Bai , Itamar Pres , Martin Wattenberg , Jonathan K. Kummerfeld , Rada Mihalcea

Despite their staggering capabilities as assistant tools, often exceeding human performances, Large Language Models (LLMs) are still prone to jailbreak attempts from malevolent users. Although red teaming practices have already identified…

Computers and Society · Computer Science 2025-05-27 Barbara Puccio , Federico Castagna , Allan Tucker , Pierangelo Veltri

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…

Machine Learning · Computer Science 2025-09-11 Lukas Toral , Teddy Lazebnik

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Computation and Language · Computer Science 2025-05-16 Michael Fire , Yitzhak Elbazis , Adi Wasenstein , Lior Rokach

Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…

Machine Learning · Computer Science 2024-08-20 Manuel Wendl , Lukas Koller , Tobias Ladner , Matthias Althoff

Trainable activation functions, whose parameters are optimized alongside network weights, offer increased expressivity compared to fixed activation functions. Specifically, trainable activation functions defined as ratios of polynomials…

Machine Learning · Computer Science 2025-07-22 Rafał Surdej , Michał Bortkiewicz , Alex Lewandowski , Mateusz Ostaszewski , Clare Lyle

Model-free reinforcement learning algorithms have exhibited great potential in solving single-task sequential decision-making problems with high-dimensional observations and long horizons, but are known to be hard to generalize across…

Machine Learning · Computer Science 2023-05-30 Boyuan Chen , Chuning Zhu , Pulkit Agrawal , Kaiqing Zhang , Abhishek Gupta

Recent works have identified a gap between research and practice in artificial intelligence security: threats studied in academia do not always reflect the practical use and security risks of AI. For example, while models are often studied…

Cryptography and Security · Computer Science 2024-03-27 Kathrin Grosse , Lukas Bieringer , Tarek Richard Besold , Alexandre Alahi

The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fixed template between the input instruction and initial model…

Computation and Language · Computer Science 2025-06-05 Chak Tou Leong , Qingyu Yin , Jian Wang , Wenjie Li