10 accepted papers
The proliferation of large language models has intensified demands for reliable content attribution, yet existing watermarking techniques face a fundamental trilemma: they cannot simultaneously optimize for robustness against attacks, minimal text quality degradation, and detection efficiency. To re
Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing attacks, and make it difficult for model owners to effectively veri
Existing ViT backdoor attacks based on backbone-overwriting full-tuning are computationally expensive and inflict performance degradation. This has forced adversaries towards the Visual Parameter-Efficient Fine-Tuning (PEFT) paradigm, dominated by adapter-based (e.g., LoRA) and prompt-based (e.g., V
Generative vision-language models like Stable Diffusion demonstrate remarkable capabilities in creative media synthesis, but they also pose substantial risks of producing unsafe, offensive, or culturally inappropriate content when prompted adversarially. Current defenses struggle to align outputs wi
Dual-arm coordination is a fundamental problem in humanoid nursing robot. Large language model (LLM)-driven dual-arm collaboration is gradually becoming a research hotspot in this field. However, the single-thread LLM task planner lacks the ability of co-scheduling, which leads to poor efficiency in
Graph Contrastive Learning(GCL) is a fundamental pretraining research method in Graph Neural Networks (GNNs), which puts rich graph-level insights into the graph data to augment the data representation. However, since the existing GCLs generally regard the intra-layer node as negative samples, they…
Texts generated by large language models (LLMs) are increasingly widespread online. Due to the lack of effective attribution mechanisms, the enforcement of copyright and the prevention of misuse remain significant challenges in the context of LLM-generated content. LLMs watermark emerges as a crucia
Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve impressive performance and efficiency by dynamically routing inputs to specialized subnetworks, known as experts. However, this sparse routing mechanism inherently exhibits task preferences due to expert specialization…
"Diffusion Models (DMs) achieve state-of-the-art synthesis results in image generation and have been applied to various fields. However, DMs sometimes seriously violate user privacy during usage, making the protection of privacy an urgent issue. Using traditional privacy computing schemes like Secur…
Backdoor attack is a type of serious security threat to deep learning models.An adversary can provide users with a model trained on poisoned data to manipulate prediction behavior in test stage using a backdoor. The backdoored models behave normally on clean images, yet can be activated and output i…