15 accepted papers
As single-center computing approaches power constraints, decentralized training becomes essential. However, traditional Reinforcement Learning (RL) methods, crucial for enhancing large model post-training, cannot adapt to decentralized distributed training due to the tight coupling between parameter…
Triggerable watermarking enables model owners to assert ownership against model extraction attacks. However, most existing approaches require additional training, which limits post-deployment flexibility, and the lack of clear theoretical foundations makes them vulnerable to adaptive attacks. In thi…
With the increasing adoption of Retrieval-Augmented Generation (RAG) systems for knowledge-intensive tasks, ensuring the adequacy of retrieved documents has become critically important for generation quality. Traditional reranking approaches face three significant challenges: substantial computation…
With the extensive deployment and application of Internet of Things (IoT) devices, vulnerable edge nodes have emerged as primary targets for Advanced Persistent Threat (APT) attacks. Attackers compromise IoT terminal devices to establish an initial foothold and subsequently exploit lateral movement
The rise of Large Language Models (LLMs) has heightened concerns about the misuse of AI-generated text, making watermarking a promising solution. Mainstream watermarking schemes for LLMs fall into two categories: logits-based and sampling-based. However, current schemes entail trade-offs among robus…
Multimedia rumor content has been widely disseminated with the rise of generative technologies. Existing rumor detection approaches typically focus independently on multi-modal data (such as text and images) or social structure analysis, and only a few researchers have attempted to integrate all thr…
Large Language Models (LLMs) excel in various domains but pose inherent privacy risks. Existing methods to evaluate privacy leakage in LLMs often use memorized prefixes or simple instructions to extract data, both of which well-alignment models can easily block. Meanwhile, Jailbreak attacks bypass L…
Deep learning-based malicious traffic detection requires large-scale, accurately labeled datasets. However, realistic malicious traffic datasets contain noisy labels due to annotation errors, which can degrade the performance of detection models. Existing methods for handling noisy labels involve ro…
Language models have shown vulnerability against backdoor attacks, threatening the security of services based on them. To mitigate the threat, existing solutions attempted to search for backdoor triggers, which can be time-consuming when handling a large search space. Looking into the attack process…
Aspect-based sentiment analysis (ABSA) aims to align aspects and corresponding sentiment expressions, so as to identify the sentiment polarities of specific aspects. Most existing ABSA methods focus on mining syntactic or semantic information, which still suffers from noisy interference introduced b…
Multi-task learning (MTL) has emerged as a promising approach for sharing inductive bias across multiple tasks to enable more efficient learning in text classification. However, training all tasks simultaneously often yields degraded performance of each task than learning them independently, since d…
Aspect-based sentiment analysis aims to identify sentiment polarity of social media users toward different aspects. Most recent methods adopt the aspect-centric latent tree to connect aspects and their corresponding opinion words, thinking that would facilitate establishing the relationship between…
Existing anomaly detection models show success in detecting abnormal images with generative adversarial networks on the insufficient annotation of anomalous samples. However, existing models cannot accurately identify the anomaly samples which are close to the normal samples. We assume that the main…
Stance detection aims to identify people’s standpoints expressed in the text towards a target, which can provide powerful information for various downstream tasks.Recent studies have proposed multi-task learning models that introduce sentiment information to boost stance detection.However, they negl…
Top-k sparsification method is popular and powerful forreducing the communication cost in Federated Learning(FL). However, according to our experimental observation, it spends most of the total communication cost on the index of the selected parameters (i.e., their position informa-tion), which is i…