2026
ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
AAAI 2026technical
Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM
4 accepted papers
Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM
Model Context Protocol (MCP) standardizes interface mapping for large language models (LLMs) to access external data and tools, which revolutionizes the paradigm of tool selection and facilitates the rapid expansion of the LLM agent tool ecosystem. However, as the MCP is increasingly adopted, third-
Deep learning models employed in face recognition (FR) systems have been shown to be vulnerable to physical adversarial attacks through various modalities, including patches, projections, and infrared radiation. However, existing adversarial examples targeting FR systems often suffer from issues suc…
Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed trigger setting (e.g., unusual words) may be easily detected by human detection, limiting the effectiveness and practicali…