相关论文: Auditing Games for Sandbagging

Predictive models often reinforce biases which were originally embedded in their training data, through skewed decisions. In such cases, mitigation methods are critical to ensure that, regardless of the prevailing disparities, model…

This work investigates the potential of undermining both fairness and detection performance in abusive language detection. In a dynamic and complex digital world, it is crucial to investigate the vulnerabilities of these detection models to…

As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untrusted AI agents by monitoring their actions and intervening or…

The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule…

Botnet detection based on machine learning have witnessed significant leaps in recent years, with the availability of large and reliable datasets that are extracted from real-life scenarios. Consequently, adversarial attacks on machine…

Many ML models are opaque to humans, producing decisions too complex for humans to easily understand. In response, explainable artificial intelligence (XAI) tools that analyze the inner workings of a model have been created. Despite these…

White-box monitors are a popular technique for detecting potentially harmful behaviours in language models. While they perform well in general, their effectiveness in detecting text-ambiguous behaviour is disputed. In this work, we find…

While there have been many proposals on making AI algorithms explainable, few have attempted to evaluate the impact of AI-generated explanations on human performance in conducting human-AI collaborative tasks. To bridge the gap, we propose…

Responsible AI is becoming critical as AI is widely used in our everyday lives. Many companies that deploy AI publicly state that when training a model, we not only need to improve its accuracy, but also need to guarantee that the model…

Edge storage presents a viable data storage alternative for application vendors (AV), offering benefits such as reduced bandwidth overhead and latency compared to cloud storage. However, data cached in edge computing systems is susceptible…

To safely deploy deep learning-based computer vision models for computer-aided detection and diagnosis, we must ensure that they are robust and reliable. Towards that goal, algorithmic auditing has received substantial attention. To guide…

Agent skills extend LLM agents with reusable instructions, tool interfaces, and executable code, and users increasingly install third-party skills from marketplaces, repositories, and community channels. Because a skill exposes both…

A concern about cutting-edge or "frontier" AI foundation models is that an adversary may use the models for preparing chemical, biological, radiological, nuclear, (CBRN), cyber, or other attacks. At least two methods can identify foundation…

Artificial intelligence-based systems for player risk detection have become central to harm prevention efforts in the gambling industry. However, growing concerns around transparency and effectiveness have highlighted the absence of…

Debugging is a crucial skill in programming education and software development, yet it is often overlooked in CS curricula. To address this, we introduce an AI-powered debugging assistant integrated into an IDE. It offers real-time support…

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…

Recent AI-related scandals have shed a spotlight on accountability in AI, with increasing public interest and concern. This paper draws on literature from public policy and governance to make two contributions. First, we propose an AI…

It is important to collect credible training samples $(x,y)$ for building data-intensive learning systems (e.g., a deep learning system). Asking people to report complex distribution $p(x)$, though theoretically viable, is challenging in…

Fairness in artificial intelligence (AI) prediction models is increasingly emphasized to support responsible adoption in high-stakes domains such as health care and criminal justice. Guidelines and implementation frameworks highlight the…

Benchmarks are important measures to evaluate safety and compliance of AI models at scale. However, they typically do not offer verifiable results and lack confidentiality for model IP and benchmark datasets. We propose Attestable Audits,…