Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection: Clarifying Problem Formulation and Experimental Protocols
arXiv:2507.18457v1 Announce Type: cross Abstract: Adversarial robustness in LiDAR-based 3D object detection is a critical research area due to its…
Bob’s Confetti: Phonetic Memorization Attacks in Music and Video Generation
arXiv:2507.17937v1 Announce Type: cross Abstract: Lyrics-to-Song (LS2) generation models promise end-to-end music synthesis from text, yet their vulnerability to training…
VeriMinder: Mitigating Analytical Vulnerabilities in NL2SQL
arXiv:2507.17896v1 Announce Type: cross Abstract: Application systems using natural language interfaces to databases (NLIDBs) have democratized data analysis. This positive…
Automated Code Review Using Large Language Models with Symbolic Reasoning
arXiv:2507.18476v1 Announce Type: cross Abstract: Code review is one of the key processes in the software development lifecycle and is…
Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbation
arXiv:2503.04151v2 Announce Type: replace-cross Abstract: Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative…
Fairness Evaluation of Large Language Models in Academic Library Reference Services
arXiv:2507.04224v2 Announce Type: replace-cross Abstract: As libraries explore large language models (LLMs) for use in virtual reference services, a key…
EXGnet: a single-lead explainable-AI guided multiresolution network with train-only quantitative features for trustworthy ECG arrhythmia classification
arXiv:2506.12404v2 Announce Type: replace-cross Abstract: Deep learning has significantly propelled the performance of ECG arrhythmia classification, yet its clinical adoption…