Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
Large language model (LLM)-based intrusion detection systems (IDS) are increasingly studied for security monitoring, yet their robustness against feasible traffic manipulation remains largely empirical. We present Traffic-Aware Randomized Smoothing (TA-RS), a classifier-agnostic certified defense that injects Gaussian noise exclusively into the directly controllable (DC) subspace -- features a remote attacker can modify -- during both fine-tuning and certification, aligning the smoothing distrib
Record details
Published: 15 July 2026
Source: arXiv
Category: Research
Topics: Military & security
Retrieved: 16 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Non-Degenerate Risk Certification for Automated Security Decisions: A Decision-Contract Theory with ATT\&CK-Aligned Triage as a Worked Instance
arXiv cs.LG · 12 August 2026
CyberSG Connect:AI, Trust and Cyber Resilience Workshop
NTU Singapore AI · 16 July 2026
Composable Trust for Language Models: A proven boundary and a measured defense
arXiv red teaming query · 14 July 2026
Cultural, Organisational, and Individual Factors Contributing to Cyber Incident Reporting: A Systematic Literature Review
Computers in Human Behavior · 14 July 2026
Online consent misread: A mixed-method study on (cyber)rape culture's influence on sexual consent perceptions and responses to unsolicited genital images
Computers in Human Behavior · 14 July 2026
SMC-ES: Automated synthesis of formally verified control policies
arXiv cs.AI · 16 July 2026
How to cite this record
ethics.ai (15 July 2026), “Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection,” evidence record 10590, https://ethics.ai/record/10590 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.