Related papers: Auditing Games for Sandbagging
AI systems can fail to learn important behaviors, leading to real-world issues like safety concerns and biases. Discovering these systematic failures often requires significant developer attention, from hypothesizing potential edge cases to…
As AI systems are increasingly used to conduct research autonomously, misaligned systems could introduce subtle flaws that produce misleading results while evading detection. We introduce Auditing Sabotage Bench, a benchmark for evaluating…
The rapid deployment of AI systems in high-stakes domains, including those classified as high-risk under the The EU AI Act (Regulation (EU) 2024/1689), has intensified the need for reliable compliance auditing. For binary classifiers,…
This paper introduces an information-theoretic method for selecting a subset of problems which gives the most information about a group of problem-solving algorithms. This method was tested on the games in the General Video Game AI (GVGAI)…
Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…
The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…
Fairness and accountability are two essential pillars for trustworthy Artificial Intelligence (AI) in healthcare. However, the existing AI model may be biased in its decision marking. To tackle this issue, we propose an adversarial…
This paper presents an intelligent and transparent AI-driven system for Credit Risk Assessment using three state-of-the-art ensemble machine learning models combined with Explainable AI (XAI) techniques. The system leverages XGBoost,…
Although attribute grammars are commonly used for compiler construction, little investigation has been conducted on debugging attribute grammars. The paper proposes two types of systematic debugging methods, an algorithmic debugging and…
As software systems grow increasingly complex, explainability has become a crucial non-functional requirement for transparency, user trust, and regulatory compliance. Eliciting explainability requirements is challenging, as different…
Some traits making a "good" AI model are hard to describe upfront. For example, should responses be more polite or more casual? Such traits are sometimes summarized as model character or personality. Without a clear objective, conventional…
The rise of machine learning (ML) is accompanied by several high-profile cases that have stressed the need for fairness, accountability, explainability and trust in ML systems. The existing literature has largely focused on fully automated…
Machine learning models are vulnerable to adversarial inputs that induce seemingly unjustifiable errors. As automated classifiers are increasingly used in industrial control systems and machinery, these adversarial errors could grow to be a…
Black-box explanation is the problem of explaining how a machine learning model -- whose internal logic is hidden to the auditor and generally complex -- produces its outcomes. Current approaches for solving this problem include model…
We propose a general approach to quantitatively assessing the risk and vulnerability of artificial intelligence (AI) systems to biased decisions. The guiding principle of the proposed approach is that any AI algorithm must outperform a…
In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent…
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…
The importance of explainability in AI has become a pressing concern, for which several explainable AI (XAI) approaches have been recently proposed. However, most of the available XAI techniques are post-hoc methods, which however may be…
As artificial intelligence (AI) becomes integral to economy and society, communication gaps between developers, users, and stakeholders hinder trust and informed decision-making. High-level AI labels, inspired by frameworks like EU energy…
While Large Language Models have achieved notable success on formal mathematics benchmarks such as MiniF2F, it remains unclear whether these results stem from genuine logical reasoning or semantic pattern matching against pre-training data.…