Research
Academic papers, new techniques, benchmarks, and theoretical findings in AI/LLM security.
Academic papers, new techniques, benchmarks, and theoretical findings in AI/LLM security.
60 items
Researchers characterize how detectable malicious injections are on the RAVEN II surgical robot, using a public dataset that pairs platform telemetry with external high-resolution encoder ground truth. They test three injection points across the command and observation paths and three injection patterns with increasing temporal dispersion, detecting at window and session timescales. Detectability depends strongly on how the injected deviation is spread over time: an abrupt step is detected well below the 1 mm clinical tolerance, while the same total deviation spread across a window or session can stay hidden from single-window statistics.
This paper presents BXLL, a Bi-LSTM stacking ensemble combined with SDN-driven honeypot engagement for adaptive intrusion detection in IoT networks. The source text provided contains only the title, publication date, journal volume and authors, so the research question, method details and findings are not stated.
The source text consists only of publication metadata: a December 2026 date, the Journal of Information Security and Applications (Volume 103), and the authors Xinfeng He and Xia Li. It contains no abstract, method, or findings, so no summary of the research can be given.
Chen, Liu, Zhai, Liu and Dai publish SSH-Tracker in the Journal of Information Security and Applications, Volume 103, in December 2026. The source text gives only publication metadata, so the research question, method and findings cannot be stated from it.
The source reports a live behavioral experiment on malicious insider threats, focusing on exfiltration, evasion and behavioral sequences. The authors are James Doodson, Deanna D. Caputo and James F. Murphy of MITRE's Insider Threat Research & Solutions group, and the paper appeared in Computers & Security on 18 September 2026. The source text provided contains only publication metadata, so the study's method and findings are not described.
Researchers Tran Ngoc Bao Huynh, Haowen Xu, Brian Almaguer, Jun Dai and Xiaoyan Sun published work in Computers & Security, available online 18 September 2026, titled "INFER: Portable hands-on labs for digital forensics education: design, deployment, and educational impact." The source text provided contains only bibliographic details and does not describe the method or findings.
Researchers ask whether a single adversarial image can consistently mislead diverse frontier MLLMs in black-box settings. They present O-Attack, a transfer-based black-box framework that exploits cross-modally aligned semantic representations in surrogate models, and report attack success rates rising on GPT-5.4 (29.1% to 77.2%), Claude-4.6 (42.8% to 81.6%), and Gemini-3.1 (38.2% to 80.9%). Across 24 MLLMs, O-Attack outperforms six state-of-the-art methods in black-box transferability.
This research asks whether adversarial training improves generalization for multi-view vision-language-action (VLA) robot policies adapted from a pretrained VLM, evaluated across seven LIBERO-Plus shift axes. Direct adversarial training substantially improves Camera Viewpoint and Sensor Noise but gives mixed or negative effects on other shifts, and it can cause view collapse, where the policy becomes dominated by the wrist view. Adding a View Swap intervention further improves Camera Viewpoint, Sensor Noise, and Robot Initial State, with mixed effects elsewhere.
Fix: The source mitigates view collapse with a simple View Swap intervention, applied before re-evaluating adversarial training.
Arxiv (cs.RO + cs.CV security)This research study tests adversarial patches for aerial perception under three physical constraints: a printer's reproducible ink gamut, the flat panel a vehicle offers, and detail loss from altitude. Measured printer gamuts raised net attack success on three of six closed-set segmentation victims, for example +0.120 on DeepLabv3-R101 and +0.041 on SegFormer-B0. A printed-decal evaluation did not detect transfer and bounds the transferred rate at 0.133.