CyberIntel ⬡ News
★ Saved ◆ Cyber Reads
← Back ◬ AI & Machine Learning Apr 13, 2026

Follow My Eyes: Backdoor Attacks on VLM-based Scanpath Prediction

arXiv Security Archived Apr 13, 2026 ✓ Full text saved

arXiv:2604.08766v1 Announce Type: new Abstract: Scanpath prediction models forecast the sequence and timing of human fixations during visual search, driving foveated rendering and attention-based interaction in mobile systems where their integrity is a first-class security concern. We present the first study of backdoor attacks against VLM-based scanpath prediction, evaluated on GazeFormer and COCO-Search18. We show that naive fixed-path attacks, while effective, create detectable clustering in

Full text archived locally
✦ AI Summary · Claude Sonnet


    Computer Science > Cryptography and Security [Submitted on 9 Apr 2026] Follow My Eyes: Backdoor Attacks on VLM-based Scanpath Prediction Diana Romero, Mutahar Ali, Momin Ahmad Khan, Habiba Farrukh, Fatima Anwar, Salma Elmalaki Scanpath prediction models forecast the sequence and timing of human fixations during visual search, driving foveated rendering and attention-based interaction in mobile systems where their integrity is a first-class security concern. We present the first study of backdoor attacks against VLM-based scanpath prediction, evaluated on GazeFormer and COCO-Search18. We show that naive fixed-path attacks, while effective, create detectable clustering in the continuous output space. To overcome this, we design two variable-output attacks: an input-aware spatial attack that redirects predicted fixations toward an attacker-chosen target object, and a scanpath duration attack that inflates fixation durations to delay visual search completion. Both attacks condition their output on the input scene, producing diverse and plausible scanpaths that evade cluster-based detection. We evaluate across three trigger modalities (visual, textual, and multimodal), multiple poisoning ratios, and five post-training defenses, finding that no defense simultaneously suppresses the attacks and preserves clean performance across all configurations. We further demonstrate that backdoor behavior survives quantization and deployment on both flagship and legacy commodity smartphones, confirming practical threat viability for edge-deployed gaze-driven systems. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2604.08766 [cs.CR]   (or arXiv:2604.08766v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.08766 Focus to learn more Submission history From: Diana Romero [view email] [v1] Thu, 9 Apr 2026 21:06:19 UTC (3,452 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 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?)
    💬 Team Notes
    Article Info
    Source
    arXiv Security
    Category
    ◬ AI & Machine Learning
    Published
    Apr 13, 2026
    Archived
    Apr 13, 2026
    Full Text
    ✓ Saved locally
    Open Original ↗