Search for: All records

With the rapid growth of large language models, big data, and malicious online attacks, it has become increasingly important to have tools for anomaly detection that can distinguish machine from human, fair from unfair, and dangerous from safe. Prior work has shown that two-distribution (specified complexity) hypothesis tests are useful tools for such tasks, aiding in detecting bias in datasets and providing artificial agents with the ability to recognize artifacts that are likely to have been designed by humans and pose a threat. However, existing work on two-distribution hypothesis tests requires exact values for the specification function, which can often be costly or impossible to compute. In this work, we prove novel finite-sample bounds that allow for two-distribution hypothesis tests with only estimates of required quantities, such as specification function values. Significantly, the resulting bounds do not require knowledge of the true distribution, distinguishing them from traditional p-values. We apply our bounds to detect student cheating on multiple-choice tests, as an example where the exact specification function is unknown. We additionally apply our results to detect representational bias in machine-learning datasets and provide artificial agents with intention perception, showing that our results are consistent with prior work despite only requiring a finite sample of the space. Finally, we discuss additional applications and provide guidance for those applying these bounds to their own work. 

Conjecturing that an agent's ability to perceive the intentions of others can increase its chances of survival, we introduce a simple game, the Hero's Dilemma, which simulates interactions between two virtual agents to investigate whether an agent's ability to detect the intentional stance of a second agent provides a measurable survival advantage. We test whether agents able to make decisions based on the perceived intention of an adversarial agent have advantages over agents without such perception, but who instead rely on a variety of different game-playing strategies. In the game, an agent must decide whether to remain hidden or attack an often more powerful agent based on the perceived intention of the other agent. We compare the survival rates of agents with and without intention perception, and find that intention perception provides significant survival advantages and is the most successful strategy in the majority of situations tested. 

We evaluate the benefits of intention perception, the ability of an agent to perceive the intentions and plans of others, in improving a software agent's survival likelihood in a simulated virtual environment. To model intention perception, we set up a multi-agent predator and prey model, where the prey agents search for food and the predator agents seek to eat the prey. We then analyze the difference in average survival rates between prey with intention perception-knowledge of which predators are targeting them-and those without. We find that intention perception provides significant survival advantages in almost all cases tested, agreeing with other recent studies investigating intention perception in adversarial situations and environmental danger assessment. 

Being able to assess and calculate risks can positively impact an agent’s chances of survival. When other intelligent agents alter environments to create traps, the ability to detect such intended traps (and avoid them) could be life-saving. We investigate whether there are cases for which an agent’s ability to perceive intention through the assessment of environmental artifacts provides a measurable survival advantage. Our agents are virtual gophers assessing a series of room-like environments, which are potentially dangerous traps intended to harm them. Using statistical hypothesis tests based on configuration coherence, the gophers differentiate between designed traps and configurations that are randomly generated and most likely safe, allowing them access to the food contained within them. We find that gophers possessing the ability to perceive intention have significantly better survival outcomes than those without intention perception in most of the cases evaluated.