4 accepted papers
Federated learning (FL) is vulnerable to backdoor attacks. Yet sustaining backdoor effectiveness under repeated aggregation remains challenging. Existing methods often rely on heuristic trigger designs or indiscriminant parameter manipulation, leading to rapid decay or detectable anomalies. In this …
Glitch tokens—inputs that trigger unpredictable or anomalous behavior in Large Language Models (LLMs)—pose significant challenges to model reliability and safety. Existing detection methods primarily rely on heuristic embedding patterns or statistical anomalies within internal representations, limit
Large Language Models (LLMs) commonly rely on explicit refusal prefixes for safety, making them vulnerable to prefix injection attacks. We introduce HumorReject, a novel data-driven approach that reimagines LLM safety by decoupling it from refusal prefixes through humor as an indirect refusal strate
Large language models (LLMs) have demonstrated remarkable capabilities, but their power comes with significant security considerations. While extensive research has been conducted on the safety of LLMs in chat mode, the security implications of their function calling feature have been largely overlo…