Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2607. 07663v1 Announce Type: new Abstract: AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses during deployment, training on data they generate, and, increasingly, conducting AI research itself.
arXiv:2607. 07471v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness.
arXiv:2602. 06838v3 Announce Type: replace Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy.
arXiv:2306. 12859v3 Announce Type: replace Abstract: Federated learning is a distributed machine learning technology, which realizes the balance between data privacy protection and data sharing computing.
arXiv:2607. 06954v1 Announce Type: new Abstract: Wearable and mobile sensing technologies have demonstrated strong potential for health inference; however, most sensor models are designed for specific disease types, limiting their transferability across different health risks.
arXiv:2607. 06856v1 Announce Type: cross Abstract: Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics.
arXiv:2607. 07375v1 Announce Type: cross Abstract: Adversarial vulnerability in deep neural networks (DNNs) has been studied from the perspectives of decision-boundary geometry, feature robustness, input-output Jacobians, and the instability of inverse problems.
arXiv:2510. 13817v2 Announce Type: replace Abstract: The growth of IoT devices in shared environments has outpaced our ability to identify them, posing urgent risks to privacy, safety, and accountability.
arXiv:2607. 06748v1 Announce Type: cross Abstract: Smart home automation platforms increasingly rely on user-authored YAML configuration files to define device behaviors, but these files are prone to syntax, formatting, and semantic logic errors that can cause automation failures and safety risks.
arXiv:2603. 16551v2 Announce Type: replace-cross Abstract: Generative models are increasingly used to augment medical imaging datasets for fairer AI, yet a key assumption often goes unexamined: that generators produce equally high-quality images across demographic groups.
arXiv:2607. 07040v1 Announce Type: new Abstract: How can we measure intelligence beyond human capability?
arXiv:2607. 07047v1 Announce Type: cross Abstract: Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety.
arXiv:2607. 06639v1 Announce Type: cross Abstract: On modular arithmetic, a network's embedding keeps compressing for tens of thousands of steps after it has already generalized.
arXiv:2607. 06623v1 Announce Type: cross Abstract: Process industries rely on time-series forecasting and soft sensing to estimate quality variables that are hard to measure online.
arXiv:2607. 06649v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sensitive examples could be unintentionally encoded, raising concerns about privacy or copyright violation.
arXiv:2602. 23802v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of human emotions.
arXiv:2607. 07397v1 Announce Type: new Abstract: Autonomous agents promise substantial gains in speed, scale, and labor efficiency, but their failures can impose abrupt and often irreversible costs.
arXiv:2607. 07357v1 Announce Type: cross Abstract: Effective social robot navigation requires sensitivity to human behavior, often revealed through subtle skeletal cues like gait and orientation.
arXiv:2607. 06643v1 Announce Type: cross Abstract: Backdoor attacks severely threaten large-scale AI models.
arXiv:2503. 15581v2 Announce Type: replace Abstract: Real-time safety assessment is critical for ensuring the reliable operation of complex dynamic systems.