GCG Attack On A Diffusion LLM
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Targeted Attack Improves Protection against Unauthorized Diffusion Customization
Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter thi…
Adversarial AttackImage GenerationMisinformationMembership Inference of Diffusion Models
Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we sy…
DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
Diffusion-based purification defenses leverage diffusion models to remove crafted perturbations of adversarial examples and achieve state-of-the-art robustness. Recent studies show that even advanced attacks cannot break…
Adversarial PurificationTrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
Diffusion models have achieved great success in a range of tasks, such as image synthesis and molecule design. As such successes hinge on large-scale training data collected from diverse sources, the trustworthiness of t…
Image GenerationDiffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Diffusion models (DMs) have emerged as a promising approach for behavior cloning (BC). Diffusion policies (DP) based on DMs have elevated BC performance to new heights, demonstrating robust efficacy across diverse tasks,…