arXiv (All)
open access
AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs
We present AKRASIA, a stealthy, inference-time backdoor attack against reasoning-based Code LLMs. AKRASIA aims to achieve a backdoor target (e.g., malicious code execution) in reasoning LLMs while evading automated defenses and human inspection. To achieve this, AKRASIA probes the victim LLM to cons
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
- AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs#627618
- Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks#432464
- RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations#229581
- SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents#10441
- SkillForge: Compositional Skill Synthesis with Verification-in-the-Loop for Generating Formally Verified Dafny Programs#798464
Record · ID 926229
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