arXiv (All)
open access
TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization
Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that this seemingly natural design is fundamentally myopic: candidates that look better under the current-step proxy often fail to produce better jailbrea
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
- TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization#809488
- Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving#971420
- MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression#329055
- HINT: Toward an Executable Hardware-Intent Representation Layer for LLM-Driven RTL Generation#635963
- HINT: Toward an Executable Hardware-Intent Representation Layer for LLM-Driven RTL Generation#633614
Record · ID 819484
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