The development of text-to-image (T2I) generative models, that enable the creation of high-quality synthetic images from textual prompts, has opened new frontiers in creative design and content generation. However, this paper reveals a significant and previously unrecognized ethical risk inherent in this technology and introduces a novel method, termed the Cognitive Morphing Attack (CogMorph), which manipulates T2I models to generate images that retain the original core subjects but embeds toxic or harmful contextual elements. This nuanced manipulation exploits the cognitive principle that human perception of concepts is shaped by the entire visual scene and its context, producing images that amplify emotional harm far beyond attacks that merely preserve the original semantics. To address this, we first construct an imagery toxicity taxonomy spanning 10 major and 48 sub-categories, aligned with human cognitive-perceptual dimensions, and further build a toxicity risk matrix resulting in 1,176 high-quality T2I toxic prompts. Based on this, our CogMorph first introduces Cognitive Toxicity Augmentation, which develops a cognitive toxicity knowledge base with rich external toxic representations for humans (e.g., fine-grained visual features) that can be utilized to further guide the optimization of adversarial prompts. In addition, we present Contextual Hierarchical Morphing, which hierarchically extracts critical parts of the original prompt (e.g., scenes, subjects, and body parts), and then iteratively retrieves and fuses toxic features to inject harmful contexts. Extensive experiments on multiple open-source T2I models and black-box commercial APIs (e.g., DALL $\cdot$ E-3) demonstrate the efficacy of CogMorph which significantly outperforms other baselines by large margins (+20.62% on average). Our codes are available at https://github.com/raykr/CogMorph. Warning: This paper contains harmful imagery that might be offensive to some readers.

This paper considers the hierarchical decision problems with $H_{\infty }$ constraint, where the proposed feedback Stackelberg strategy incorporates a two-level control progress. The leader first announces his action at the beginning of the game and anticipates the follower's optimal response, the follower chooses a response to optimize his/her cost function with the information of the leader's action. The optimal action of the leader, coupled with the rational response of the follower, forms a Stackelberg equilibrium. Both the leader and the follower exchange their observations and historical control inputs. Under the assumption of linear feedback strategies, the problems are converted into unsolved feedback gain matrix. The introduced Pontryagin's maximum principle develops a solution based on the forward and backward stochastic difference equations (FBSDEs). The separation principle is proposed to deal with coupled state estimation gains and optimal controller gains. To this end, the necessary and sufficient solvability conditions for both finite horizon and infinite horizon case are derived.

The rapid progress of generative AI has enabled remarkable creative capabilities, yet it also raises urgent concerns regarding the safety of AI-generated visual content in real-world applications such as content moderation, platform governance, and digital media regulation. This includes unsafe material such as sexually explicit images, violent scenes, hate symbols, propaganda, and unauthorized imitations of copyrighted artworks. Existing image safety systems often rely on rigid category filters and produce binary outputs, lacking the capacity to interpret context or reason about nuanced, adversarially induced forms of harm. In addition, standard evaluation metrics (e.g., attack success rate) fail to capture the semantic severity and dynamic progression of toxicity. To address these limitations, we propose Perception–Retrieval–Judgement (PRJ), a cognitively inspired framework that models toxicity detection as a structured reasoning process. PRJ follows a three-stage design: it first transforms an image into descriptive language (perception), then retrieves external knowledge related to harm categories and traits (retrieval), and finally evaluates toxicity based on legal or normative rules (judgement). This language-centric structure enables the system to detect both explicit and implicit harms with improved interpretability and categorical granularity. In addition, we introduce a dynamic scoring mechanism based on a contextual toxicity risk matrix to quantify harmfulness across different semantic dimensions. Experiments show that PRJ surpasses existing safety checkers in detection accuracy and robustness while uniquely supporting structured category-level toxicity interpretation.