arXiv (OAI Expanded)
open access
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks. In this paper, we introduce $\mathtt{maxEntropy}$, an entropy-based poisonin
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions#352996
- PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization#157313
- IMV-sLSTM: An Intrinsically Interpretable Architecture for Network Intrusion Detection Systems#332997
- Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL#793277
- Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL#789273
Record · ID 1083961
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive