
Minh Nhat Le, Nisarga Gondi, Yibo Peng, Ronghao Ni, Limin Jia, Beidi Chen, Haizhong Zheng · arXiv (Cornell University) 2026 · 2026
DOI: 10.48550/arxiv.2609.36603
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Large language models (LLMs) increasingly power agents that access sensitive information, use external tools, and modify software repositories. Although these capabilities offer substantial benefits, they also create security risks such as jailbreaks, prompt injection, and vulnerable code generation. Existing defenses often require retraining, fail to adapt to evolving attacks, or address only a single threat pattern. To address these limitations, we propose Self-Evolving Defense (SED), a training-free framework that distills harmful agent trajectories into reusable security policies without updating model weights. By retrieving relevant policies for future tasks, SED continually adapts to new attacks while retaining knowledge across attack scenarios. To evaluate the effectiveness of SED, we test it with three open-source models (DeepSeek V4 Flash, GLM 5.2, and Kimi K3) on eight benchmarks that span jailbreaks, prompt injection, and insecure code generation. SED lowers targeted prompt-injection success on AGENTDOJO to 0.42%, compared with 3.7% for the best baseline defense, and holds adaptive X-TEAMING attack success on HARMBENCH to 7.8%, more than four times lower than the best baseline at 35.2%, while preserving benign task utility.
No comments yet — start the discussion below.