Related papers: EXTree: Towards Supporting Explainability in Attri…
Role-Based Access Control (RBAC) struggles to adapt to dynamic enterprise environments with documents that contain information that cannot be disclosed to specific user groups. As these documents are used by LLM-driven systems (e.g., in…
Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…
Algorithmic accountability scholarship has focused heavily on explanation, helping affected parties understand why decisions were made. We argue this focus is insufficient. Explanation without evidentiary access does not enable meaningful…
Recently, XACML is a popular access control policy language that is used widely in many applications. Policies in XACML are built based on many components over distributed resources. Due to the expressiveness of XACML, it is not trivial for…
Despite outperforming the human in many tasks, deep neural network models are also criticized for the lack of transparency and interpretability in decision making. The opaqueness results in uncertainty and low confidence when deploying such…
In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier…
Interactive Artificial Intelligence (AI) agents are becoming increasingly prevalent in society. However, application of such systems without understanding them can be problematic. Black-box AI systems can lead to liability and…
Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and LIME, while intuitive, may deviate from the model's…
Behavior Trees constitute a widespread AI tool which has been successfully spun out in robotics. Their advantages include simplicity, modularity, and reusability of code. However, Behavior Trees remain a high-level decision making engine;…
Access control (AC) is the core of every architectural solution for information security. Indeed, no effective protection scheme can abstract from the careful design of access control policies, and infrastructures underlying modern…
Trustworthy Artificial Intelligence solutions are essential in today's data-driven applications, prioritizing principles such as robustness, safety, transparency, explainability, and privacy among others. This has led to the emergence of…
The era of big data has promoted the vigorous development of many industries, boosting the full potential of holistic data-driven analysis. Hadoop has become the primary choice for mainstream platforms used by stakeholders to process big…
Forward reachability analysis is a dominant approach for verifying reach-avoid specifications in neural feedback systems, i.e., dynamical systems controlled by neural networks, and a number of directions have been proposed and studied. In…
The rapidly advancing domain of Explainable Artificial Intelligence (XAI) has sparked significant interests in developing techniques to make AI systems more transparent and understandable. Nevertheless, in real-world contexts, the methods…
Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning requires (1) a feature space composed of human-understandable…
We describe an access control model that has been implemented in the web content management framework "Deme" (which rhymes with "team"). Access control in Deme is an example of what we call "bivalent relation object access control"(BROAC).…
Behavior Trees are a task switching policy representation that can grant reactiveness and fault tolerance. Moreover, because of their structure and modularity, a variety of methods can be used to generate them automatically. In this short…
Security risk management can be applied on well-defined or existing systems; in this case, the objective is to identify existing vulnerabilities, assess the risks and provide for the adequate countermeasures. Security risk management can…
This paper describes our ongoing work on security verification against inference attacks on data trees. We focus on infinite secrecy against inference attacks, which means that attackers cannot narrow down the candidates for the value of…
The high performance of tree ensemble classifiers benefits from a large set of rules, which, in turn, makes the models hard to understand. To improve interpretability, existing methods extract a subset of rules for approximation using model…