Related papers: Scheming in the wild: detecting real-world AI sche…
Mature industrial sectors (e.g., aviation) collect their real world failures in incident databases to inform safety improvements. Intelligent systems currently cause real world harms without a collective memory of their failings. As a…
Synthetic participants represent a methodologically concerning concept that threatens the integrity of UX research. Findings from previous experiments specify how AI outputs are misaligned with the behaviors and thoughts of real humans in…
Out-of-Domain (OOD) intent detection is important for practical dialog systems. To alleviate the issue of lacking OOD training samples, some works propose synthesizing pseudo OOD samples and directly assigning one-hot OOD labels to these…
Recognizing speaking in humans is a central task towards understanding social interactions. Ideally, speaking would be detected from individual voice recordings, as done previously for meeting scenarios. However, individual voice recordings…
Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to identify both seen and unseen anomalies during testing. Current approaches rely on simple…
The tasks of out-of-domain (OOD) intent discovery and generalized intent discovery (GID) aim to extend a closed intent classifier to open-world intent sets, which is crucial to task-oriented dialogue (TOD) systems. Previous methods address…
Artificial intelligence (AI) is rapidly transforming healthcare, enabling fast development of tools like stress monitors, wellness trackers, and mental health chatbots. However, rapid and low-barrier development can introduce risks of bias,…
Recent large-scale events like election fraud and financial scams have shown how harmful coordinated efforts by human groups can be. With the rise of autonomous AI systems, there is growing concern that AI-driven groups could also cause…
Recent advancements in pre-trained language models have enabled convenient methods for generating human-like text at a large scale. Though these generation capabilities hold great potential for breakthrough applications, it can also be a…
With the development of mobile social networks, more and more crowdsourced data are generated on the Web or collected from real-world sensing. The fragment, heterogeneous, and noisy nature of online/offline crowdsourced data, however, makes…
Open-source software serves as a foundation for the internet and the cyber supply chain, but its exploitation is becoming increasingly prevalent. While advances in vulnerability detection for OSS have been significant, prior research has…
Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI metrics to support pre-specified…
Identifying user intents from natural language utterances is a crucial step in conversational systems that has been extensively studied as a supervised classification problem. However, in practice, new intents emerge after deploying an…
Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models (LLMs). We run an extensive, fine-grained analysis on the…
As our professional, social, and financial existences become increasingly digitized and as our government, healthcare, and military infrastructures rely more on computer technologies, they present larger and more lucrative targets for…
The advancement of Internet-of-Things (IoT) edge devices with various types of sensors enables us to harness diverse information with Mobile Crowd-Sensing applications (MCS). This highly dynamic setting entails the collection of ubiquitous…
Online social networks (OSNs) play a crucial role in today's world. On the one hand, they allow free speech, information sharing, and social-movements organization, to cite a few. On the other hand, they are the tool of choice to spread…
Controlling physics-based humanoids from natural-language instructions is a critical step toward general-purpose embodied agents. However, existing methods remain constrained by a tension between semantic expressiveness and physical…
The accelerating adoption of large language models, retrieval-augmented generation pipelines, and multi-agent AI workflows has created a structural governance crisis. Organizations cannot govern what they cannot see, and existing compliance…
Fraudulent activities are rapidly evolving, employing increasingly diverse and sophisticated methods that pose serious threats to individuals, organizations, and society. This paper proposes the FIST Framework (Fraud Incident Structured…