Related papers: Security Incentivization: An Empirical Study of ho…
A distributed machine learning platform needs to recruit many heterogeneous worker nodes to finish computation simultaneously. As a result, the overall performance may be degraded due to straggling workers. By introducing redundancy into…
Reward hacking is a form of misalignment in which models overoptimize proxy rewards without genuinely solving the underlying task. Precisely measuring reward hacking occurrence remains challenging because true task rewards are often…
Performance metrics measuring in Financial Integrity systems are crucial for maintaining an efficient and cost effective operation. An important performance metric is False Positive Rate. This metric cannot be directly monitored since we…
We present and evaluate a large-scale malware detection system integrating machine learning with expert reviewers, treating reviewers as a limited labeling resource. We demonstrate that even in small numbers, reviewers can vastly improve…
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and…
The focus on rapid software delivery inevitably results in the accumulation of technical debt, which, in turn, affects quality and slows future development. Yet, companies with a long history of rapid delivery exist. Our primary aim is to…
We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…
Software development teams establish elaborate continuous integration pipelines containing automated test cases to accelerate the development process of software. Automated tests help to verify the correctness of code modifications…
Software security vulnerabilities can lead to severe consequences, making early detection essential. Although code review serves as a critical defense mechanism against security flaws, relevant feedback remains scarce due to limited…
The Department of Homeland Security in the United States estimates that 90% of software vulnerabilities can be traced back to defects in design and software coding. The financial impact of these vulnerabilities has been shown to exceed 380…
Cybersecurity education is considered an important part of undergraduate computing curricula, but many institutions teach it only in dedicated courses or tracks. This optionality risks students graduating with limited exposure to secure…
AI coding scaffolds like Claude Code and Codex use retrying: blocking actions flagged as risky and continuing the trajectory. We study retrying from an AI control perspective, which treats the model as potentially adversarial. We find that…
Security is a requirement of utmost importance to produce high-quality software. However, there is still a considerable amount of vulnerabilities being discovered and fixed almost weekly. We hypothesize that developers affect the…
Modern code generation models exhibit longer outputs, accelerated capability growth, and changed training dynamics, rendering traditional training methodologies, algorithms, and datasets ineffective for improving their performance. To…
The problem of secret-key based authentication under a privacy constraint on the source sequence is considered. The identifier measurements during authentication are assumed to be controllable via a cost-constrained "action" sequence.…
As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises in this setup, as the agent optimizes for passing tests…
AI systems that output their reasoning in natural language offer an opportunity for safety -- we can \emph{monitor} their chain of thought (CoT) for undesirable reasoning, such as the pursuit of harmful objectives. However, the extent to…
The field of Artificial Intelligence (AI) is going through a period of great expectations, introducing a certain level of anxiety in research, business and also policy. This anxiety is further energised by an AI race narrative that makes…
Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly…
During code reviews, an essential step in software quality assurance, reviewers have the difficult task of understanding and evaluating code changes to validate their quality and prevent introducing faults to the codebase. This is a tedious…