Cordyceps: Covert Control Attacks on LLMs via Data Poisoning

Computer Science > Cryptography and Security [Submitted on 26 May 2026] Cordyceps: Covert Control Attacks on LLMs via Data Poisoning Zedian Shao, Charles Fleming, Teodora Baluta Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization, or online monitoring can neutralize. In this paper, we propose a data poisoning method that teaches an LLM an information hiding scheme reliably and stealthily through semantic associations between shared knowledge such as facts or concepts and attacker-chosen phrases. The induced hiding scheme can encode and decode arbitrary malicious instructions, thus revealing a new and subtle poisoning-induced vulnerability: covert control attacks. We precisely characterize covert control attacks and evaluate them across 5 LLMs, 3 backdoor defenses, and 4 prompt injection defenses. With a small poisoned fraction, covert control attacks outperform heuristic-based prompt injection attacks in average attack success rate by about 40\% relative to clean fine-tuned models. They also circumvent defenses based on detection and fine-tuning, maintaining up to 93\% attack success rate after backdoor defenses and up to 98\% after prompt injection defenses. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2605.26595 [cs.CR]   (or arXiv:2605.26595v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.26595 Focus to learn more Submission history From: Zedian Shao [view email] [v1] Tue, 26 May 2026 06:28:30 UTC (1,906 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)