ML Security PapersGCG Attack On A Diffusion LLM
Ruben Neyroud, Sam Corley · University of Illinois at Urbana-Champaign
Adapts gradient-based GCG adversarial attacks to LLaDA diffusion LLM, exploring prefix and suffix variants to elicit harmful outputs
While most LLMs are autoregressive, diffusion-based LLMs have recently emerged as an alternative method for generation. Greedy Coordinate Gradient (GCG) attacks have proven effective against autoregressive models, but their applicability to diffusion language models remains largely unexplored. In this work, we present an exploratory study of GCG-style adversarial prompt attacks on LLaDA (Large Language Diffusion with mAsking), an open-source diffusion LLM. We evaluate multiple attack variants, including prefix perturbations and suffix-based adversarial generation, on harmful prompts drawn from the AdvBench dataset. Our study provides initial insights into the robustness and attack surface of diffusion language models and motivates the development of alternative optimization and evaluation strategies for adversarial analysis in this setting.