Safety, Security, and Cognitive Risks in Neuro-Symbolic AI

Computer Science > Cryptography and Security [Submitted on 15 Jun 2026] Safety, Security, and Cognitive Risks in Neuro-Symbolic AI Manoj Parmar Neuro-symbolic AI (NeSy) pairs neural perception with symbolic reasoning, making it attractive for high-stakes domains where explainability and structured inference are required. However, this hybrid architecture introduces an enlarged attack surface spanning five layers: neural perception, symbolic knowledge bases, reasoning engines, agentic orchestration, and data stores -- each exploitable in ways absent from purely neural systems. This paper makes six contributions: (1) formal definitions of NeSy Attack Surface, Symbolic Integrity Violation (SIV), and Cross-Layer Amplification Ratio \mathcal{X}, decomposed into neural-caused and autonomous symbolic sensitivity components; (2) a unified threat model extending MITRE ATLAS with 11 NeSy-specific tactic extensions and a five-profile attacker taxonomy; (3) a symbolic-layer threat catalogue covering knowledge graph (KG) poisoning, ontology-merging, and inference-engine subversion; (4) analysis of cognitive risks -- automation bias, authority bias, and sycophantic reinforcement -- structurally amplified by NeSy's explicit logical explanations relative to black-box neural outputs; (5) interdisciplinary mitigations with measurable acceptance criteria aligned to NIST AI 600-1 and the EU AI Act; (6) three empirical benchmarks: (E1) targeted KG poisoning achieves break-even SIV at injection budget B=5 on a 205-entity medical KG, with a KG-specific stealth/SIV trade-off; (E2) PGD-10 at \varepsilon=0.01 yields \mathcal{X}=5.884 (95% CI [4.64,\, 8.00], p<0.0001), confirmed adversarially specific by a matched-random baseline (E^{R}_{\mathrm{rand}}=0), on a DistilBERT+ProbLog pipeline; (E3) single-axiom OWL edits achieve 93.3% SIV success with 100% Pellet-consistency stealth, but held-out STIX detection fails at 50% (random-guessing level), an open problem. Comments: 28 pages, 1 figure, 10 tables Subjects: Cryptography and Security (cs.CR) ACM classes: I.2.6; I.2.3; K.6.5 Report number: V202606 Cite as: arXiv:2606.17223 [cs.CR]   (or arXiv:2606.17223v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2606.17223 Focus to learn more Submission history From: Manojkumar Parmar [view email] [v1] Mon, 15 Jun 2026 19:11:55 UTC (233 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-06 Change to browse by: cs 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?)