Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models

Computer Science > Artificial Intelligence [Submitted on 4 Aug 2026] Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models Mario Leiva, Yue Ma, Qinru Qiu, Gerardo Simari, Paulo Shakarian Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures. Prior metacognitive methods learn logical rules that flag a model's errors, but rely on hand-authored domain-knowledge cues (object-size priors, segmentation masks) that do not transfer to genuinely novel scenes. We show that this metacognitive layer can be learned without any domain knowledge by exploiting vector-space geometry: per-model Label Vector Pools (LVP), built from each model's own training embeddings, yield error-detection rules from the geometry of detections relative to training-determined prototypes, reaching parity with domain-knowledge rules to within 0.002 every F1 on test set. Because the approach remains neurosymbolic, these geometric rules share a single logical framework and can still be complemented by domain knowledge when available. We frame the fusion of multiple imperfect ViT-based detectors as a consistency-based abduction problem solved at test time by an exact Integer Program (IP) and a polynomial-time heuristic. On an aerial-imagery benchmark of 15 weather-shifted test sets and six ViT detectors, our domain-knowledge-free layer matches the strongest majority-vote variant on clean data (within 0.005 F1) and, unlike every majority-vote baseline, retains its performance under a coordinated label-flipping attack: at a 90% flip rate it averages 0.42 F1 versus 0.35 for MV-Plurality (a 22% relative gain) and attains the highest F1 on \emph{every} test set once the flip rate exceeds 0.4 Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Logic in Computer Science (cs.LO) Cite as: arXiv:2608.04190 [cs.AI]   (or arXiv:2608.04190v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2608.04190 Focus to learn more Submission history From: Mario Leiva [view email] [v1] Tue, 4 Aug 2026 19:46:57 UTC (6,917 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.CV cs.LG cs.LO References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)