Related papers: Comment on "Learning to Build the Bomb"

In work [1] (Yu. N. Pokotilovski, arXiv:0902.3425v2) restrictions on constants of pseudo-magnetic interaction gSgP are presented. These restrictions are considerably differed from restrictions on gSgP, before published in work [2] (A.P.…

In this paper we seek to quantify the ability of learning to improve safety guarantees endowed by Control Barrier Functions (CBFs). In particular, we investigate how model uncertainty in the time derivative of a CBF can be reduced via…

Contemporary robots have become exceptionally skilled at achieving specific tasks in structured environments. However, they often fail when faced with the limitless permutations of real-world unstructured environments. This motivates…

In a recent paper, Kalamidas has advanced a new proposal of faster than light communication which has not yet been proved invalid. In this paper we show that, as all previous proposals, it does not work. The mistake arises from an…

This paper argues that training AI systems with absolute constraints -- which forbid certain acts irrespective of the amount of value they might produce -- may make considerable progress on many AI safety problems in principle. First, it…

Modern nuclear structure theory is rapidly evolving towards regions of exotic short-lived nuclei far from stability, nuclear astrophysics applications, and bridging the gap between low-energy QCD and the phenomenology of finite nuclei. The…

Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers…

The human's cognitive capacity for problem solving is always limited to his/her educational background, skills, experiences, etc. Hence, it is often insufficient to bring solution to extraordinary problems especially when there is a time…

I am a second-year cognitive science major, and as a student who has completed my physical science distribution requirements, I will likely never again encounter Gauss's law. So why do I feel that the time and effort I devoted to solving…

While reinforcement learning algorithms have had great success in the field of autonomous navigation, they cannot be straightforwardly applied to the real autonomous systems without considering the safety constraints. The later are crucial…

Two cooperating, autonomous mobile robots with arbitrary nonzero max speeds are placed at arbitrary initial positions in the plane. A remotely detonated bomb is discovered at some source location and must be moved to a safe distance away…

Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability, however, is challenged in this paper. We identify a novel…

Artificial intelligence has not yet revolutionized the design of materials and molecules. In this perspective, we identify four barriers preventing the integration of atomistic deep learning, molecular science, and high-performance…

For all its successes, Reinforcement Learning (RL) still struggles to deliver formal guarantees on the closed-loop behavior of the learned policy. Among other things, guaranteeing the safety of RL with respect to safety-critical systems is…

In an information-rich world, people's time and attention must be divided among rapidly changing information sources and the diverse tasks demanded of them. How people decide which of the many sources, such as scientific articles or…

As quantum computing continues to advance, the development of quantum-secure neural networks is crucial to prevent adversarial attacks. This paper proposes three quantum-secure design principles: (1) using post-quantum cryptography, (2)…

In this paper we explore the theoretical boundaries of planning in a setting where no model of the agent's actions is given. Instead of an action model, a set of successfully executed plans are given and the task is to generate a plan that…

Safety constraints are crucial to the development of mission-critical systems. The practice of developing software for systems of this type requires reliable methods for identifying and analysing project artefacts. This paper proposes a…

Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poisoning attacks when malicious clients send false updates to the…

We discuss models and data of crowd disasters, crime, terrorism, war and disease spreading to show that conventional recipes, such as deterrence strategies, are often not effective and sufficient to contain them. Many common approaches do…