TopoBudget: Persistent-Connectivity-Preserving Web Graph Sparsification for Reusable Community Analytics
2026-08-11T08:52:08Z•9b2d0bbbe327edeef438274ba0f05bfc2315a9308c9f4507d2563ad1f0b00280
IoT securityLLMTikTok data collectionacademic researchadversarial machine learningcontent moderationdisinformationevasion attacksgraph analyticsopinion dynamicssocial media
What happened
An arXiv RSS collection containing research on graph sparsification, TikTok data acquisition, network centrality, IoT power control, agent-based social dynamics, SocialFi simulation, perceptions of AI financial advice, adversarial testing of LLM-generated disinformation detectors, and opinion polarization control. The security-relevant item studies iterative adversarial rewriting—including back-translation and LLM persona-based transformations—that evades social-media disinformation classifiers, achieving up to a 95% label-flip rate while often preserving the original meaning. No direct system
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_si
- Record identifier
- 9b2d0bbbe327edeef438274ba0f05bfc2315a9308c9f4507d2563ad1f0b00280
- Enrichment time
- 2026-08-11T08:52:08Z
- 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.