Wenmin Li

Wenmin Li, Shunsuke Sakai, Zhongkai Zhao et al.

Diffusion-based dataset distillation has recently emerged as a promising paradigm for condensing large-scale datasets into compact synthetic sets. By leveraging pretrained generative priors, these methods can produce realistic class-conditional samples more efficiently than traditional matching-based approaches. However, most existing diffusion-based methods still adopt a rigid ``Generate-and-Use'' strategy, where the generated samples are directly treated as the final distilled set under a fixed images-per-class budget. Such a design tightly couples candidate generation with final budget allocation, which may result in redundant waste of the limited budget or insufficiently informative samples. In this paper, we propose ``Pool-Select-Refine'', a two-stage framework for allocation-aware generative dataset distillation. First, instead of directly using a fixed number of generated samples, we construct an over-complete candidate pool and select a compact subset under the target budget. Second, we refine the selected samples in latent space using soft-label supervision derived from the teacher model, improving semantic alignment while preserving the generative prior. This design explicitly decouples generation, selection, and refinement, enabling more effective use of the distillation budget. Experiments on large-scale and fine-grained image classification benchmarks show that the proposed framework delivers consistent gains over diffusion-based baselines. The results suggest that introducing a curation stage before refinement is a simple yet effective way to improve diffusion-based dataset distillation.

Wenmin Li, Shunsuke Sakai, Tatsuhito Hasegawa

Deploying machine learning models in resource-constrained environments, such as edge devices or rapid prototyping scenarios, increasingly demands distillation of large datasets into significantly smaller yet informative synthetic datasets. Current dataset distillation techniques, particularly Trajectory Matching methods, optimize synthetic data so that the model's training trajectory on synthetic samples mirrors that on real data. While demonstrating efficacy on medium-scale synthetic datasets, these methods fail to adequately preserve semantic richness under extreme sample scarcity. To address this limitation, we propose a novel dataset distillation method integrating contrastive learning during image synthesis. By explicitly maximizing instance-level feature discrimination, our approach produces more informative and diverse synthetic samples, even when dataset sizes are significantly constrained. Experimental results demonstrate that incorporating contrastive learning substantially enhances the performance of models trained on very small-scale synthetic datasets. This integration not only guides more effective feature representation but also significantly improves the visual fidelity of the synthesized images. Experimental results demonstrate that our method achieves notable performance improvements over existing distillation techniques, especially in scenarios with extremely limited synthetic data.

Mingyu Yu, Wei Wang, Yanjie Wei et al.

Recent advancements in adversarial jailbreak attacks have exposed critical vulnerabilities in Large Language Models (LLMs), enabling the circumvention of alignment safeguards through increasingly sophisticated prompt manipulations. Based on our experiments, we found that the effectiveness of jailbreak strategies is influenced by the comprehension ability of the attacked LLM. Building on this insight, we propose a capability-aware Multi-Encryption Framework (MEF) for evaluating vulnerabilities in black-box LLMs. Specifically, MEF first categorizes the comprehension ability level of the LLM, then applies different strategies accordingly: For models with limited comprehension ability, MEF adopts the Fu+En1 strategy, which integrates layered semantic mutations with an encryption technique, more effectively contributing to evasion of the LLM's defenses at the input and inference stages. For models with strong comprehension ability, MEF uses a more complex Fu+En1+En2 strategy, in which additional dual-ended encryption techniques are applied to the LLM's responses, further contributing to evasion of the LLM's defenses at the output stage. Experimental results demonstrate the effectiveness of our approach, achieving attack success rates of 98.9% on GPT-4o (29 May 2025 release) and 99.8% on GPT-4.1 (8 July 2025 release). Our work contributes to a deeper understanding of the vulnerabilities in current LLM alignment mechanisms.

Haiyan Sun, Qiaoyan Wen, Hua Zhang et al.

Recently, two certificateless three-party authenticated key agreement protocols were proposed, and both protocols were claimed they can meet the desirable security properties including forward security, key compromise impersonation resistance and so on. Through cryptanalysis, we show that one neither meets forward security and key compromise impersonation resistance nor resists an attack by an adversary who knows all users' secret values, and the other cannot resist key compromise impersonation attack. Finally, we propose improved protocols to make up two original protocols' security weaknesses, respectively. Further security analysis shows that our improved protocols can remove such security weaknesses.