Text-guided inpainting models are widely used for image editing, restoration, and content generation due to their ability to produce high-fidelity results aligned with natural language prompts. However, these models remain vulnerable to jailbreaking attacks, where adversaries manipulate inputs to generate pornographic or violent content. While prior attacks rely on adversarial text prompts, they are increasingly mitigated by advanced text-based safety filters and manual review. In this work, we propose a new attack paradigm that bypasses these defenses by leveraging the image modality alone. Specifically, we inject imperceptible adversarial perturbations into the input image, enabling successful jailbreaks even when paired with clean prompts (e.g., ''a woman''). To achieve this, we address two key challenges: (1) stabilizing the optimization of adversarial perturbations via a novel gradient estimator, and (2) ensuring visual imperceptibility through a diffusion-based perturbation generator. Extensive experiments show that our method successfully compromises the Stable Diffusion Inpainting model-despite its built-in image and text safety checkers-achieving an average attack success rate (ASR) of 85.7%, significantly outperforming baselines (58.7%). Moreover, our attack exhibits strong transferability across models and maintains robustness against common image pre-processing defenses. Warning: Blurred or masked NSFW imagery is contained.

Deep learning-based face recognition systems are increasingly deployed in security-critical applications, yet remain vulnerable to adversarial attacks. Existing physical attacks often lack stealth or realism, limiting their utility for evaluating realworld robustness. To address this, we propose BadLogo, a physically realizable, sticker-based perturbation that balances attack effectiveness and visual plausibility. We also introduce PLOF-GAN, an attack model employing a two-stage pretraining strategy to progressively transform benign logos into high-quality adversarial patches. An improved 3D mapping algorithm ensures precise alignment with facial geometry, enhancing the realism of physical deployment. To quantitatively assess stealthiness and visual plausibility, we design a new metric, BROI, which measures both region occlusion and semantic coherence. Whether in evasion or impersonation attack scenarios, extensive experiments on identity verification and identification tasks demonstrate that BadLogo achieves high attack success rates with superior stealthiness compared to existing methods. Notably, our approach exhibits strong transferability across multiple face recognition models and generalizes to object detection scenarios. By leveraging adversarial stickers, this work reveals critical vulnerabilities in face recognition systems under physical-world conditions and offers new perspectives for developing more robust models.

In AVS and H.264/AVC, Lagrangian Rate distortion (RD) optimization techniques are widely adopted for coding mode selection and displacement vector estimation. The optimal Lagrange multipliers in these two cases are both floating-point values. If RD optimized video encoder is implemented on computation-constrained fixed-point platform such as FPGA and ASIC, fixed-point Lagrange multiplier selection is an important problem to trade-off the RD performance and computation complexity. This work focuses on fixed-point Lagrange multiplier selection for RD mode decision. Adaptive scaling matrix is used to trade-off complexity and RD performance. Also, intensive simulation results and analysis on precision, hardware cost, and RD performance are given. The proposed approach is also well-suited for RD optimized motion estimation for computation-constrained video coding.