Related papers: Auto-ART: Structured Literature Synthesis and Auto…

The deployment of autonomous robots in safety-critical applications requires safety guarantees. Provably safe reinforcement learning is an active field of research that aims to provide such guarantees using safeguards. These safeguards…

Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To mitigate these vulnerabilities, adversarial training and…

Modern AI systems increasingly comprise multiple interconnected neural networks to tackle complex inference tasks. Testing such systems for robustness and safety entails significant challenges. Current state-of-the-art robustness testing…

Semi-supervised learning (SSL) has shown considerable potential in medical image segmentation, primarily leveraging consistency regularization and pseudo-labeling. However, many SSL approaches only pay attention to low-level consistency and…

Retrieval-Augmented Generation (RAG) has become critical for knowledge-intensive applications, yet evaluating its performance in vertical domains remains difficult due to domain complexity, diverse context scales, and heavy reliance on…

Recent natural language processing (NLP) techniques have accomplished high performance on benchmark datasets, primarily due to the significant improvement in the performance of deep learning. The advances in the research community have led…

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…

Though deep neural networks have achieved the state of the art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. In this paper, we develop improved techniques…

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learning systems (e.g., GNNs). Existing solutions typically rely…

While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investigated robustification mechanisms and reliable defenses. We…

LLM applications are AI systems whose nondeterministic outputs and evolving model behavior make traditional testing insufficient for release governance. We present an automated self-testing framework that introduces quality gates with…

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some recent works have shown…

We introduce compute-grounded reasoning (CGR), a design paradigm for spatial-aware research agents in which every answerable sub-problem is resolved by deterministic computation before a language model is asked to generate. Spatial Atlas…

Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. To address these systemic vulnerabilities, we present AdvSynGNN, a comprehensive…

Large Language Models (LLMs) are increasingly applied to tasks involving structured inputs such as graphs. Abstract Meaning Representations (AMRs), which encode rich semantics as directed graphs, offer a rigorous testbed for evaluating LLMs…

Safe reinforcement learning deals with mitigating or avoiding unsafe situations by reinforcement learning (RL) agents. Safe RL approaches are based on specific risk representations for particular problems or domains. In order to analyze…

Model robustness against adversarial examples of single perturbation type such as the $\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their…

Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to explore existing knowledge for a research problem, or to…

Considerable advancements have been achieved in SLAM methods tailored for structured environments, yet their robustness under challenging corner cases remains a critical limitation. Although multi-sensor fusion approaches integrating…