Controllability-Aware Adversarial Examples Against LLM-Based Network Traffic Classifiers

arXiv 2607.07739•cd6f56b82056a48d8c94807cb60d7b403a8c207a59da8d71d4fcbdb024c04094
KS-CFARISC-VScopeJudgeTEEadversarial-mlagent-monitoringcontrol-flow-attestationcontrollability-aware-attacksdataset-releaseforensic-schemaforensicsidsjailbreaksllm-securitymechanistic-interpretabilitynetwork-intrusion-detectionoffensive-securitypre-execution-gatingpsychological-manipulationscope-enforcementsocial-engineeringsymbolic-replayt2i-safetytext-to-imagetransfer-attacks

Paper metadata

arXiv ID
2607.07739
Version
Not specified by this published record
Category
Computer Science — Cryptography and Security (cs.CR)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_cr
Record identifier
cd6f56b82056a48d8c94807cb60d7b403a8c207a59da8d71d4fcbdb024c04094
Enrichment time
2026-07-10T07:23:34Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

Controllability-Aware Adversarial Examples Against LLM-Based Network Traffic Classifiers · Baitaphish