English
Related papers

Related papers: Subversion Strategy Eval: Can language models stat…

200 papers

In this work we present a formal theoretical framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. Our results apply to general multi-class classifiers that map from an…

Machine Learning · Computer Science 2021-01-01 Ivan Y. Tyukin , Desmond J. Higham , Alexander N. Gorban

Artificial Intelligence (AI) increasingly shows its potential to outperform predicate logic algorithms and human control alike. In automatically deriving a system model, AI algorithms learn relations in data that are not detectable for…

Artificial Intelligence · Computer Science 2022-10-12 Simon Daniel Duque Anton , Daniel Schneider , Hans Dieter Schotten

In this paper we present a computational modeling account of an active self in artificial agents. In particular we focus on how an agent can be equipped with a sense of control and how it arises in autonomous situated action and, in turn,…

Artificial Intelligence · Computer Science 2021-12-13 Sebastian Kahl , Sebastian Wiese , Nele Russwinkel , Stefan Kopp

Artificial Intelligence (AI) holds the potential to dramatically improve patient care. However, it is not infallible, necessitating human-AI-collaboration to ensure safe implementation. One aspect of AI safety is the models' ability to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Anna M. Wundram , Christian F. Baumgartner

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Computation and Language · Computer Science 2023-10-05 Xianjun Yang , Xiao Wang , Qi Zhang , Linda Petzold , William Yang Wang , Xun Zhao , Dahua Lin

While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk is emerging: capability-oriented training induced exploitation. We investigate whether language models, when…

Machine Learning · Computer Science 2026-02-13 Yujun Zhou , Yue Huang , Han Bao , Kehan Guo , Zhenwen Liang , Pin-Yu Chen , Tian Gao , Werner Geyer , Nuno Moniz , Nitesh V Chawla , Xiangliang Zhang

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting…

Robotics · Computer Science 2025-09-16 James C. Ward , Alex Bott , Connor York , Edmund R. Hunt

Despite considerable efforts on making them robust, real-world AI-based systems remain vulnerable to decision based attacks, as definitive proofs of their operational robustness have so far proven intractable. Canonical robustness…

Artificial Intelligence · Computer Science 2025-05-07 Ilias Tsingenopoulos , Vera Rimmer , Davy Preuveneers , Fabio Pierazzi , Lorenzo Cavallaro , Wouter Joosen

Artificial Intelligence (AI) agents have rapidly evolved from specialized, rule-based programs to versatile, learning-driven autonomous systems capable of perception, reasoning, and action in complex environments. The explosion of data,…

In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user's expectation. We frame Explainable AI Planning in the context of the plan negotiation problem, in which a succession of…

Artificial Intelligence · Computer Science 2021-03-30 Benjamin Krarup , Senka Krivic , Daniele Magazzeni , Derek Long , Michael Cashmore , David E. Smith

Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better…

Computation and Language · Computer Science 2025-12-08 José Pombal , Maya D'Eon , Nuno M. Guerreiro , Pedro Henrique Martins , António Farinhas , Ricardo Rei

We tackle the question of whether an agent can, by suitable choice of prompts, control an AI bot to any state. To that end, we first introduce a formal definition of ``meaning'' that is amenable to analysis. Then, we characterize…

Artificial Intelligence · Computer Science 2023-05-31 Stefano Soatto , Paulo Tabuada , Pratik Chaudhari , Tian Yu Liu

As artificial intelligence (AI) assistants become more widely adopted in safety-critical domains, it becomes important to develop safeguards against potential failures or adversarial attacks. A key prerequisite to developing these…

Human-Computer Interaction · Computer Science 2025-04-04 Abed Kareem Musaffar , Anand Gokhale , Sirui Zeng , Rasta Tadayon , Xifeng Yan , Ambuj Singh , Francesco Bullo

We propose nearly-optimal control strategies for changing states of a quantum system. We argue that quantum control optimization can be studied analytically within some protocol families that depend on a small set of parameters for…

Quantum Physics · Physics 2017-09-13 Chen Sun , Avadh Saxena , Nikolai A. Sinitsyn

Recent advancements in large language models (LLMs) have shown significant promise in various domains, especially robotics. However, most prior LLM-based work in robotic applications either directly predicts waypoints or applies LLMs within…

Robotics · Computer Science 2025-10-01 Yue Meng , Fei Chen , Yongchao Chen , Chuchu Fan

Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…

Artificial Intelligence · Computer Science 2026-01-26 Zhibo Liang , Tianze Hu , Zaiye Chen , Mingjie Tang

The stochastic nature of artificial intelligence (AI) models introduces risk to business applications that use AI models without careful consideration. This paper offers an approach to use AI techniques to gain insights on the usage of the…

Computers and Society · Computer Science 2019-06-26 Aleksander Slominski , Vinod Muthusamy , Vatche Ishakian

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of…

Machine Learning · Computer Science 2023-02-23 Shashwat Goel , Ameya Prabhu , Amartya Sanyal , Ser-Nam Lim , Philip Torr , Ponnurangam Kumaraguru

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

Artificial Intelligence · Computer Science 2025-07-25 Alberto Hernández-Espinosa , Felipe S. Abrahão , Olaf Witkowski , Hector Zenil