Wonwoo Choi, Minjae Seo, Minkyoo Song, Hwanjo Heo, Seungwon Shin, Myoungsung You · ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026 · 2026
DOI: 10.1145/3830454.3832687
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).
The rapid evolution of text-to-image (T2I) models has enabled high-fidelity visual synthesis on a global scale. However, these advancements have introduced significant security risks, particularly regarding the generation of harmful content. Politically sensitive content, such as fabricated depictions of public figures, poses severe threats when weaponized for fake news or propaganda. Despite its criticality, the robustness of current T2I safety filters against such politically motivated adversarial prompting remains underexplored. In response, we propose PC2, the first black-box political jailbreaking framework for T2I models. It exploits a novel vulnerability where safety filters evaluate political sensitivity based on linguistic context. PC2 operates through: (1) Identity-Preserving Descriptive Mapping to obfuscate sensitive keywords into neutral descriptions, and (2) Geopolitically Distal Translation to map these descriptions into fragmented, low-sensitivity languages. This strategy prevents filters from linking toxic relationships between political entities within prompts, effectively bypassing detection. We construct a new benchmark of 240 prompts designed to elicit politically sensitive images spanning 36 public figures. Evaluation on commercial T2I models, specifically the GPT series, shows that while all original prompts are blocked, PC2 achieves attack success rates (ASRs) of up to 86% and significantly outperforms state-of-the-art attack methods. We further propose a ready-to-deploy multi-layered defense against PC2-style attacks, reducing ASRs to 11%.
Last synced
This work has 2 recorded citations, but citing papers have not been linked locally yet.
No comments yet — start the discussion below.