Search for: All records

Principled accountability for autonomous decision-making in uncertain environments requires distinguishing intentional outcomes from negligent designs from actual accidents. We propose analyzing the behavior of autonomous agents through a quantitative measure of the evidence of intentional behavior. We model an uncertain environment as a Markov Decision Process (MDP). For a given scenario, we rely on probabilistic model checking to compute the ability of the agent to influence reaching a certain event. We call this the scope of agency. We say that there is evidence of intentional behavior if the scope of agency is high and the decisions of the agent are close to being optimal for reaching the event. Our method applies counterfactual reasoning to automatically generate relevant scenarios that can be analyzed to increase the confidence of our assessment. In a case study, we show how our method can distinguish between 'intentional' and 'accidental' traffic collisions. 

Hardware IP verification requires collaboration from several parties, including the 3PIP vendor, IP user, and EDA tool vendor, all of whom could threaten the design's integrity and confidentiality. Various frameworks and tools, including the IEEE 1735 standard, have been developed to address these concerns. However, these solutions fall short of the zero trust model's requirements. To overcome this, we propose a novel zero trust formal verification framework that incorporates secure multiparty computation to ensure the privacy of all the parties involved in the verification process. The efficiency of the framework is demonstrated by checking various open-source IP-level benchmarks.