arXiv (All)
open access
AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with white-box access to one model to compromise independently deployed systems. This creates a shared vulnerability across models, yet existing defenses are
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
- Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs#246459
- TULIP: Targeted LLM Unlearning at Layers Identified Per-Input#1128854
- Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates#1116390
- The Scissors Effect: When Resize-Based Input Diversity Helps or Hurts Transfer Attacks#1123137
- Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification#618516
Record · ID 1116933
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