Trust in a decision-making system requires both safety guarantees and the ability to interpret and understand its behavior. This is particularly important for learned systems, whose decision-making processes are often highly opaque. Shielding is a prominent model-based technique for enforcing safety in reinforcement learning. However, because shields are automatically synthesized using rigorous formal methods, their decisions are often similarly difficult for humans to interpret. Recently, decision trees became customary to represent controllers and policies.

Side-channel analysis (SCA) poses a real-world threat by exploiting unintentional physical signals to extract secret information from secure devices. Evaluation labs also use the same techniques to certify device security. In recent years, deep learning has emerged as a prominent method for SCA, achieving state-ofthe-art attack performance at the cost of interpretability. Understanding how neural networks extract secrets is crucial for security evaluators aiming to defend against such attacks, as only by understanding the attack can one propose better countermeasures. In this work, we apply mechanistic interpretability to neural networks trained for SCA, revealing how models exploit what leakage in side-channel traces. We focus on sudden jumps in performance to reverse engineer learned representations, ultimately recovering secret masks and moving the evaluation process from blackbox to white-box. Our results show that mechanistic interpretability can scale to realistic SCA settings, even when relevant inputs are sparse, model accuracies are low, and side-channel protections prevent standard input interventions.

The other is GRL-SVO(NUP), a fast heuristic providing a total order directly.

The objective is to maximize cumulative reward byexploring the actions to discover optimal ones (having the best expectedreward),balancedwithexploitingthem.

Notably, modern tools for the verification of hybrid automata are designed formodels thatrarely haveoverhundred discrete states [7],while arbitrary meshes grow exponentially as the granularity increases.

The reason is discussed in Appendix E. A library

Existingmethods assume that the examples illustrating a concept are mapped in a fixed direction oftheDNN'slatent space.